{"task":"3D Point Cloud Classification","dataset":"ScanObjectNN","metric_names":["Overall Accuracy","Mean Accuracy","OBJ-BG (OA)","OBJ-ONLY (OA)","FLOPs","Number of params"],"rows":[{"id":83406,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"OmniVec2","metrics":{"Overall Accuracy":"97.2"},"paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Srivastava_OmniVec2_-_A_Novel_Transformer_based_Network_for_Large_Scale_CVPR_2024_paper.html","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","paper_date":"2024-01-01","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83407,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointGST","metrics":{"OBJ-BG (OA)":"99.48","OBJ-ONLY (OA)":"97.76","Overall Accuracy":"96.18"},"paper_url":"https://arxiv.org/abs/2410.08114v1","paper_title":"Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning","paper_date":"2024-10-10","code_links":[{"title":"jerryfeng2003/pointgst","url":"https://github.com/jerryfeng2003/pointgst"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83408,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"OmniVec","metrics":{"Overall Accuracy":"96.1"},"paper_url":"https://arxiv.org/abs/2311.05709v1","paper_title":"OmniVec: Learning robust representations with cross modal sharing","paper_date":"2023-11-07","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83409,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"GPSFormer","metrics":{"FLOPs":"0.7G","Mean Accuracy":"93.8","Number of params":"2.36M","Overall Accuracy":"95.4"},"paper_url":"https://arxiv.org/abs/2407.13519v2","paper_title":"GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding","paper_date":"2024-07-18","code_links":[{"title":"changshuowang/GPSFormer","url":"https://github.com/changshuowang/GPSFormer"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83410,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ReCon++","metrics":{"OBJ-BG (OA)":"98.80","OBJ-ONLY (OA)":"97.59","Overall Accuracy":"95.25"},"paper_url":"https://arxiv.org/abs/2402.17766v3","paper_title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","paper_date":"2024-02-27","code_links":[{"title":"qizekun/ShapeLLM","url":"https://github.com/qizekun/ShapeLLM"},{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83411,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"AsymDSD-B* (no voting)","metrics":{"OBJ-BG (OA)":"96.73","OBJ-ONLY (OA)":"94.32","Overall Accuracy":"93.72"},"paper_url":"https://arxiv.org/abs/2506.21724v1","paper_title":"Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning","paper_date":"2025-06-26","code_links":[{"title":"RFLeijenaar/AsymDSD","url":"https://github.com/RFLeijenaar/AsymDSD"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83412,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointGPT","metrics":{"OBJ-BG (OA)":"97.2","OBJ-ONLY (OA)":"96.6","Overall Accuracy":"93.4"},"paper_url":"https://arxiv.org/abs/2305.11487v2","paper_title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","paper_date":"2023-05-19","code_links":[{"title":"CGuangyan-BIT/PointGPT","url":"https://github.com/CGuangyan-BIT/PointGPT"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83413,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"GPSFormer-elite","metrics":{"Mean Accuracy":"92.51","Number of params":"0.68M","Overall Accuracy":"93.30"},"paper_url":"https://arxiv.org/abs/2407.13519v2","paper_title":"GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding","paper_date":"2024-07-18","code_links":[{"title":"changshuowang/GPSFormer","url":"https://github.com/changshuowang/GPSFormer"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83414,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Mamba3D","metrics":{"FLOPs":"3.9G","Number of params":"16.9M","OBJ-BG (OA)":"94.49","OBJ-ONLY (OA)":"92.43","Overall Accuracy":"92.64"},"paper_url":"https://arxiv.org/abs/2404.14966v2","paper_title":"Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model","paper_date":"2024-04-23","code_links":[{"title":"xhanxu/Mamba3D","url":"https://github.com/xhanxu/Mamba3D"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83415,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Mamba3D (no voting)","metrics":{"FLOPs":"3.9G","Number of params":"16.9M","OBJ-BG (OA)":"92.94","OBJ-ONLY (OA)":"92.08","Overall Accuracy":"91.81"},"paper_url":"https://arxiv.org/abs/2404.14966v2","paper_title":"Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model","paper_date":"2024-04-23","code_links":[{"title":"xhanxu/Mamba3D","url":"https://github.com/xhanxu/Mamba3D"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83416,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP-2 + PointNeXt","metrics":{"Mean Accuracy":"91.2","Number of params":"1.4M","Overall Accuracy":"91.5"},"paper_url":"https://arxiv.org/abs/2305.08275v4","paper_title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","paper_date":"2023-05-14","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83417,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ReCon","metrics":{"OBJ-BG (OA)":"95.35","OBJ-ONLY (OA)":"93.80","Overall Accuracy":"91.26"},"paper_url":"https://arxiv.org/abs/2302.02318v2","paper_title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","paper_date":"2023-02-05","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"aHapBean/PCP-MAE","url":"https://github.com/aHapBean/PCP-MAE"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83418,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP-2 + PointNeXt (no voting)","metrics":{"Mean Accuracy":"90.3","Number of params":"1.4M","Overall Accuracy":"90.8"},"paper_url":"https://arxiv.org/abs/2305.08275v4","paper_title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","paper_date":"2023-05-14","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83419,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ReCon (no voting)","metrics":{"OBJ-BG (OA)":"95.18","OBJ-ONLY (OA)":"93.29","Overall Accuracy":"90.63"},"paper_url":"https://arxiv.org/abs/2302.02318v2","paper_title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","paper_date":"2023-02-05","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"aHapBean/PCP-MAE","url":"https://github.com/aHapBean/PCP-MAE"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83420,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"AsymDSD-S (no voting)","metrics":{"OBJ-BG (OA)":"94.32","OBJ-ONLY (OA)":"91.91","Overall Accuracy":"90.53"},"paper_url":"https://arxiv.org/abs/2506.21724v1","paper_title":"Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning","paper_date":"2025-06-26","code_links":[{"title":"RFLeijenaar/AsymDSD","url":"https://github.com/RFLeijenaar/AsymDSD"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83421,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DeLA","metrics":{"FLOPs":"1.5G","Mean Accuracy":"89.3","Number of params":"5.3M","Overall Accuracy":"90.4"},"paper_url":"https://arxiv.org/abs/2308.16532v1","paper_title":"Decoupled Local Aggregation for Point Cloud Learning","paper_date":"2023-08-31","code_links":[{"title":"matrix-asc/dela","url":"https://github.com/matrix-asc/dela"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83422,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PCP-MAE","metrics":{"OBJ-BG (OA)":"95.52","OBJ-ONLY (OA)":"94.32","Overall Accuracy":"90.35"},"paper_url":"https://arxiv.org/abs/2408.08753v2","paper_title":"PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders","paper_date":"2024-08-16","code_links":[{"title":"aHapBean/PCP-MAE","url":"https://github.com/aHapBean/PCP-MAE"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83423,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointConT","metrics":{"Mean Accuracy":"88.5","Overall Accuracy":"90.3"},"paper_url":"https://arxiv.org/abs/2303.04599v1","paper_title":"Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space","paper_date":"2023-03-08","code_links":[{"title":"yahuiliu99/pointcont","url":"https://github.com/yahuiliu99/pointcont"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83424,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-RAE (no voting)","metrics":{"OBJ-BG (OA)":"95.53","OBJ-ONLY (OA)":"93.63","Overall Accuracy":"90.28"},"paper_url":"https://arxiv.org/abs/2310.03670v1","paper_title":"Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning","paper_date":"2023-09-25","code_links":[{"title":"liuyyy111/point-rae","url":"https://github.com/liuyyy111/point-rae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83425,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-FEMAE","metrics":{"OBJ-BG (OA)":"95.18","OBJ-ONLY (OA)":"93.29","Overall Accuracy":"90.22"},"paper_url":"https://arxiv.org/abs/2312.10726v1","paper_title":"Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders","paper_date":"2023-12-17","code_links":[{"title":"zyh16143998882/aaai24-pointfemae","url":"https://github.com/zyh16143998882/aaai24-pointfemae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83426,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"I2P-MAE (no voting)","metrics":{"OBJ-BG (OA)":"94.15","OBJ-ONLY (OA)":"91.57","Overall Accuracy":"90.11"},"paper_url":"https://arxiv.org/abs/2212.06785v1","paper_title":"Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders","paper_date":"2022-12-13","code_links":[{"title":"zrrskywalker/i2p-mae","url":"https://github.com/zrrskywalker/i2p-mae"},{"title":"zrrskywalker/point-m2ae","url":"https://github.com/zrrskywalker/point-m2ae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83427,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP + PointNeXt","metrics":{"Mean Accuracy":"88.6","Number of params":"1.4M","Overall Accuracy":"89.7"},"paper_url":"https://arxiv.org/abs/2212.05171v4","paper_title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","paper_date":"2022-12-10","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83428,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ReCon+PPT","metrics":{"OBJ-BG (OA)":"95.01","OBJ-ONLY (OA)":"93.28","Overall Accuracy":"89.52"},"paper_url":"https://arxiv.org/abs/2408.11567v1","paper_title":"Positional Prompt Tuning for Efficient 3D Representation Learning","paper_date":"2024-08-21","code_links":[{"title":"zsc000722/ppt","url":"https://github.com/zsc000722/ppt"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83429,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"3D-JEPA","metrics":{"OBJ-BG (OA)":"93.63","OBJ-ONLY (OA)":"94.49","Overall Accuracy":"89.52"},"paper_url":"https://arxiv.org/abs/2409.15803v1","paper_title":"3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning","paper_date":"2024-09-24","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83430,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointMLP∗ + JM3D","metrics":{"Mean Accuracy":"88.7","Overall Accuracy":"89.5"},"paper_url":"https://arxiv.org/abs/2308.02982v2","paper_title":"Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation","paper_date":"2023-08-06","code_links":[{"title":"mr-neko/jm3d","url":"https://github.com/mr-neko/jm3d"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83431,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP + PointMLP","metrics":{"Mean Accuracy":"88.5","Overall Accuracy":"89.4"},"paper_url":"https://arxiv.org/abs/2212.05171v4","paper_title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","paper_date":"2022-12-10","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83432,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"KPConvX-L","metrics":{"Mean Accuracy":"88.1","Overall Accuracy":"89.3"},"paper_url":"https://arxiv.org/abs/2405.13194v1","paper_title":"KPConvX: Modernizing Kernel Point Convolution with Kernel Attention","paper_date":"2024-05-21","code_links":[{"title":"apple/ml-kpconvx","url":"https://github.com/apple/ml-kpconvx"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83433,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"P2P","metrics":{"Number of params":"195.8M","Overall Accuracy":"89.3"},"paper_url":"https://arxiv.org/abs/2208.02812v2","paper_title":"P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting","paper_date":"2022-08-04","code_links":[{"title":"wangzy22/P2P","url":"https://github.com/wangzy22/P2P"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83434,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ACT","metrics":{"Overall Accuracy":"89.17"},"paper_url":"https://arxiv.org/abs/2212.08320v2","paper_title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","paper_date":"2022-12-16","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83435,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Ours","metrics":{"Mean Accuracy":"87.2","Overall Accuracy":"89.0"},"paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320324004631","paper_title":"Beyond local patches: Preserving global–local interactions by enhancing self-attention via 3D point cloud tokenization","paper_date":"2024-11-01","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83436,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"OTMae3D","metrics":{"FLOPs":"6.29","OBJ-BG (OA)":"92.9","OBJ-ONLY (OA)":"92.3","Overall Accuracy":"89.0"},"paper_url":"https://ieeexplore.ieee.org/document/10815033","paper_title":"Rethinking Masked Representation Learning for 3D Point Cloud Understanding","paper_date":"2024-12-26","code_links":[{"title":"OpenSpaceAI/OTMae3D","url":"https://github.com/OpenSpaceAI/OTMae3D"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83437,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP-2 + Point-BERT","metrics":{"Overall Accuracy":"89.0"},"paper_url":"https://arxiv.org/abs/2305.08275v4","paper_title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","paper_date":"2023-05-14","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83438,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNeXt+Local","metrics":{"Mean Accuracy":"87.4","Overall Accuracy":"88.6"},"paper_url":"https://arxiv.org/abs/2212.05140v2","paper_title":"Local Neighborhood Features for 3D Classification","paper_date":"2022-12-09","code_links":[{"title":"VimsLab/Local3DFeatures","url":"https://github.com/VimsLab/Local3DFeatures"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83439,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"SPoTr","metrics":{"Mean Accuracy":"86.8","Overall Accuracy":"88.6"},"paper_url":"https://arxiv.org/abs/2303.16450v1","paper_title":"Self-positioning Point-based Transformer for Point Cloud Understanding","paper_date":"2023-03-29","code_links":[{"title":"mlvlab/spotr","url":"https://github.com/mlvlab/spotr"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83440,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"IDPT","metrics":{"OBJ-BG (OA)":"93.12","Overall Accuracy":"88.51"},"paper_url":"https://arxiv.org/abs/2304.07221v2","paper_title":"Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models","paper_date":"2023-04-14","code_links":[{"title":"zyh16143998882/iccv23-idpt","url":"https://github.com/zyh16143998882/iccv23-idpt"},{"title":"zyh16143998882/IDPT","url":"https://github.com/zyh16143998882/IDPT"},{"title":"zyh16143998882/aaai24-pointfemae","url":"https://github.com/zyh16143998882/aaai24-pointfemae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83441,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointMLP+TAP","metrics":{"Overall Accuracy":"88.5"},"paper_url":"https://arxiv.org/abs/2307.14971v2","paper_title":"Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models","paper_date":"2023-07-27","code_links":[{"title":"wangzy22/tap","url":"https://github.com/wangzy22/tap"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83442,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNeXt+GAM","metrics":{"FLOPs":"1.64G","Number of params":"1.4M","Overall Accuracy":"88.4"},"paper_url":"http://arxiv.org/abs/1505.07110v2","paper_title":"$(0, 4)$ dualities","paper_date":"2015-12-14","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83443,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNeXt+HyCoRe","metrics":{"Mean Accuracy":"87.0","Overall Accuracy":"88.3"},"paper_url":"https://arxiv.org/abs/2209.10318v1","paper_title":"Rethinking the compositionality of point clouds through regularization in the hyperbolic space","paper_date":"2022-09-21","code_links":[{"title":"diegovalsesia/hycore","url":"https://github.com/diegovalsesia/hycore"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83444,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ACT (no voting)","metrics":{"OBJ-BG (OA)":"93.29","OBJ-ONLY (OA)":"91.91","Overall Accuracy":"88.21"},"paper_url":"https://arxiv.org/abs/2212.08320v2","paper_title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","paper_date":"2022-12-16","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83445,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNeXt","metrics":{"FLOPs":"1.64G","Mean Accuracy":"86.8","Number of params":"1.4M","Overall Accuracy":"88.2"},"paper_url":"https://arxiv.org/abs/2206.04670v2","paper_title":"PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies","paper_date":"2022-06-09","code_links":[{"title":"guochengqian/pointnext","url":"https://github.com/guochengqian/pointnext"},{"title":"linhaojia13/pointmetabase","url":"https://github.com/linhaojia13/pointmetabase"},{"title":"boyden/pointtransformerfl","url":"https://github.com/boyden/pointtransformerfl"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83446,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointConT (no voting)","metrics":{"Mean Accuracy":"86.0","Overall Accuracy":"88.0"},"paper_url":"https://arxiv.org/abs/2303.04599v1","paper_title":"Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space","paper_date":"2023-03-08","code_links":[{"title":"yahuiliu99/pointcont","url":"https://github.com/yahuiliu99/pointcont"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83447,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointVector-S","metrics":{"Mean Accuracy":"86.2","Overall Accuracy":"87.8"},"paper_url":"https://arxiv.org/abs/2205.10528v3","paper_title":"PointVector: A Vector Representation In Point Cloud Analysis","paper_date":"2022-05-21","code_links":[{"title":"guochengqian/openpoints","url":"https://github.com/guochengqian/openpoints/blob/master/models/backbone/pointvector.py"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83448,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"point2vec","metrics":{"Mean Accuracy":"86.0","OBJ-BG (OA)":"91.2","OBJ-ONLY (OA)":"90.4","Overall Accuracy":"87.5"},"paper_url":"https://arxiv.org/abs/2303.16570v2","paper_title":"Point2Vec for Self-Supervised Representation Learning on Point Clouds","paper_date":"2023-03-29","code_links":[{"title":"kabouzeid/point2vec","url":"https://github.com/kabouzeid/point2vec"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83449,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointStack","metrics":{"Mean Accuracy":"86.2","Overall Accuracy":"87.2"},"paper_url":"https://arxiv.org/abs/2205.09962v1","paper_title":"Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling","paper_date":"2022-05-20","code_links":[{"title":"LongerVision/PointStack","url":"https://github.com/LongerVision/PointStack"},{"title":"kaist-avelab/PointStack","url":"https://github.com/kaist-avelab/PointStack"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83450,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-PN","metrics":{"Number of params":"0.8M","Overall Accuracy":"87.1"},"paper_url":"https://arxiv.org/abs/2303.08134v2","paper_title":"Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis","paper_date":"2023-03-14","code_links":[{"title":"zrrskywalker/point-nn","url":"https://github.com/zrrskywalker/point-nn"},{"title":"opengvlab/cafo","url":"https://github.com/opengvlab/cafo"},{"title":"asalarpour/Point_GN","url":"https://github.com/asalarpour/Point_GN"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83451,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointCMT","metrics":{"Mean Accuracy":"84.8","Number of params":"12.6M","Overall Accuracy":"86.7"},"paper_url":"https://arxiv.org/abs/2210.04208v1","paper_title":"Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis","paper_date":"2022-10-09","code_links":[{"title":"yanx27/2dpass","url":"https://github.com/yanx27/2dpass"},{"title":"zhanheshen/pointcmt","url":"https://github.com/zhanheshen/pointcmt"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83452,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-JEPA","metrics":{"OBJ-BG (OA)":"92.9±0.4","Overall Accuracy":"86.6"},"paper_url":"https://arxiv.org/abs/2404.16432v5","paper_title":"Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud","paper_date":"2024-04-25","code_links":[{"title":"Ayumu-J-S/Point-JEPA","url":"https://github.com/Ayumu-J-S/Point-JEPA"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83453,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointMLS","metrics":{"Overall Accuracy":"86.6"},"paper_url":"https://arxiv.org/abs/2401.08210v1","paper_title":"ModelNet-O: A Large-Scale Synthetic Dataset for Occlusion-Aware Point Cloud Classification","paper_date":"2024-01-16","code_links":[{"title":"fanglaosi/pointmls","url":"https://github.com/fanglaosi/pointmls"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83454,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-M2AE","metrics":{"OBJ-BG (OA)":"91.22","OBJ-ONLY (OA)":"88.81","Overall Accuracy":"86.43"},"paper_url":"https://arxiv.org/abs/2205.14401v2","paper_title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","paper_date":"2022-05-28","code_links":[{"title":"zrrskywalker/i2p-mae","url":"https://github.com/zrrskywalker/i2p-mae"},{"title":"zrrskywalker/point-m2ae","url":"https://github.com/zrrskywalker/point-m2ae"},{"title":"MindSpore-paper-code-2/code400","url":"https://github.com/MindSpore-paper-code-2/code400/tree/main/MAE"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83455,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP + PointBERT","metrics":{"Overall Accuracy":"86.4"},"paper_url":"https://arxiv.org/abs/2212.05171v4","paper_title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","paper_date":"2022-12-10","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83456,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DualMLP","metrics":{"Overall Accuracy":"86.4"},"paper_url":"https://link.springer.com/article/10.1007/s00371-023-03114-3","paper_title":"DualMLP: a two-stream fusion model for 3D point cloud classification","paper_date":"2023-10-10","code_links":[{"title":"snehaputul/DualMLP","url":"https://github.com/snehaputul/DualMLP"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83457,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"RepSurf-U (2x)","metrics":{"FLOPs":"2.43G","Number of params":"6.80M","Overall Accuracy":"86.0"},"paper_url":"https://arxiv.org/abs/2205.05740v2","paper_title":"Surface Representation for Point Clouds","paper_date":"2022-05-11","code_links":[{"title":"hancyran/RepSurf","url":"https://github.com/hancyran/RepSurf"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83458,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointMLP","metrics":{"Mean Accuracy":"84.4","Overall Accuracy":"85.7"},"paper_url":"https://arxiv.org/abs/2202.07123v2","paper_title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","paper_date":"2022-02-15","code_links":[{"title":"ma-xu/pointmlp-pytorch","url":"https://github.com/ma-xu/pointmlp-pytorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83459,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-LGMask","metrics":{"OBJ-BG (OA)":"89.8","OBJ-ONLY (OA)":"89.3","Overall Accuracy":"85.3"},"paper_url":"https://ieeexplore.ieee.org/abstract/document/10146493","paper_title":"Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking","paper_date":"2023-06-08","code_links":[{"title":"TangYuan96/Point-LGMask","url":"https://github.com/TangYuan96/Point-LGMask"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83460,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-MAE","metrics":{"OBJ-BG (OA)":"90.02","OBJ-ONLY (OA)":"88.29","Overall Accuracy":"85.2"},"paper_url":"https://arxiv.org/abs/2203.06604v2","paper_title":"Masked Autoencoders for Point Cloud Self-supervised Learning","paper_date":"2022-03-13","code_links":[{"title":"Pang-Yatian/Point-MAE","url":"https://github.com/Pang-Yatian/Point-MAE"},{"title":"lmd0311/pointmamba","url":"https://github.com/lmd0311/pointmamba"},{"title":"vvrpanda/exppoint-mae","url":"https://github.com/vvrpanda/exppoint-mae"},{"title":"liujia99/tpm","url":"https://github.com/liujia99/tpm"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83461,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"MVTN+SimpleView++","metrics":{"Overall Accuracy":"84.8"},"paper_url":"https://ieeexplore.ieee.org/document/9874679","paper_title":"SimpleView++: Neighborhood Views for Point Cloud Classification","paper_date":"2022-09-08","code_links":[{"title":"VimsLab/SimpleViewPlusPlus","url":"https://github.com/VimsLab/SimpleViewPlusPlus"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83462,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DeltaConv","metrics":{"Overall Accuracy":"84.7"},"paper_url":"https://arxiv.org/abs/2111.08799v5","paper_title":"DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds","paper_date":"2021-11-16","code_links":[{"title":"rubenwiersma/deltaconv","url":"https://github.com/rubenwiersma/deltaconv"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83463,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"RepSurf-U","metrics":{"FLOPs":"0.81G","Number of params":"1.48M","Overall Accuracy":"84.6"},"paper_url":"https://arxiv.org/abs/2205.05740v2","paper_title":"Surface Representation for Point Clouds","paper_date":"2022-05-11","code_links":[{"title":"hancyran/RepSurf","url":"https://github.com/hancyran/RepSurf"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83464,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"APP-Net","metrics":{"Overall Accuracy":"84.1"},"paper_url":"https://arxiv.org/abs/2205.00847v2","paper_title":"APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification","paper_date":"2022-05-02","code_links":[{"title":"mcg-nju/app-net","url":"https://github.com/mcg-nju/app-net"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83465,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointMLP-elite","metrics":{"Mean Accuracy":"81.8","Overall Accuracy":" 83.8"},"paper_url":"https://arxiv.org/abs/2202.07123v2","paper_title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","paper_date":"2022-02-15","code_links":[{"title":"ma-xu/pointmlp-pytorch","url":"https://github.com/ma-xu/pointmlp-pytorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83466,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNet++ + SageMix","metrics":{"Overall Accuracy":"83.7"},"paper_url":"https://arxiv.org/abs/2210.06944v1","paper_title":"SageMix: Saliency-Guided Mixup for Point Clouds","paper_date":"2022-10-13","code_links":[{"title":"mlvlab/SageMix","url":"https://github.com/mlvlab/SageMix"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83467,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DGCNN + SageMix","metrics":{"Overall Accuracy":"83.6"},"paper_url":"https://arxiv.org/abs/2210.06944v1","paper_title":"SageMix: Saliency-Guided Mixup for Point Clouds","paper_date":"2022-10-13","code_links":[{"title":"mlvlab/SageMix","url":"https://github.com/mlvlab/SageMix"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83468,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-TnT","metrics":{"FLOPs":"1.19G","Mean Accuracy":"81.0","Number of params":"3.9M","Overall Accuracy":"83.5"},"paper_url":"https://arxiv.org/abs/2204.03957v1","paper_title":"Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition","paper_date":"2022-04-08","code_links":[{"title":"axeber01/point-tnt","url":"https://github.com/axeber01/point-tnt"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83469,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-BERT","metrics":{"OBJ-BG (OA)":"87.43","OBJ-ONLY (OA)":"88.12","Overall Accuracy":"83.1"},"paper_url":"https://arxiv.org/abs/2111.14819v2","paper_title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","paper_date":"2021-11-29","code_links":[{"title":"julie-tang00/point-bert","url":"https://github.com/julie-tang00/point-bert"},{"title":"lulutang0608/Point-BERT","url":"https://github.com/lulutang0608/Point-BERT"},{"title":"lmd0311/pointmamba","url":"https://github.com/lmd0311/pointmamba"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":83470,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"MVTN","metrics":{"OBJ-BG (OA)":"92.6","OBJ-ONLY (OA)":"92.3","Overall Accuracy":"82.8"},"paper_url":"https://arxiv.org/abs/2011.13244v3","paper_title":"MVTN: Multi-View Transformation Network for 3D Shape Recognition","paper_date":"2020-11-26","code_links":[{"title":"ajhamdi/MVTN","url":"https://github.com/ajhamdi/MVTN"},{"title":"ajhamdi/mvtorch","url":"https://github.com/ajhamdi/mvtorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83471,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PRA-Net","metrics":{"Mean Accuracy":"79.1","Overall Accuracy":"82.1"},"paper_url":"https://arxiv.org/abs/2112.04903v1","paper_title":"PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis","paper_date":"2021-12-09","code_links":[{"title":"xiwuchen/pra-net","url":"https://github.com/xiwuchen/pra-net"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83472,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DynamicScale","metrics":{"Overall Accuracy":"82.0"},"paper_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9565556","paper_title":"Dynamic Local Geometry Capture in 3D PointCloud Classification","paper_date":"2021-10-19","code_links":[{"title":"VimsLab/DynamicScale","url":"https://github.com/VimsLab/DynamicScale"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83473,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PatchAugment","metrics":{"Mean Accuracy":"79.7","Overall Accuracy":"81.0"},"paper_url":"https://openaccess.thecvf.com/content/ICCV2021W/DLGC/html/Sheshappanavar_PatchAugment_Local_Neighborhood_Augmentation_in_Point_Cloud_Classification_ICCVW_2021_paper.html","paper_title":"PatchAugment: Local Neighborhood Augmentation in Point Cloud Classification","paper_date":"2021-10-19","code_links":[{"title":"VimsLab/PatchAugment","url":"https://github.com/VimsLab/PatchAugment"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83474,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"GBNet","metrics":{"Mean Accuracy":"77.8","Overall Accuracy":"80.5"},"paper_url":"https://arxiv.org/abs/1911.12885v5","paper_title":"Geometric Back-projection Network for Point Cloud Classification","paper_date":"2019-11-28","code_links":[{"title":"ShiQiu0419/GFNet","url":"https://github.com/ShiQiu0419/GFNet"},{"title":"ShiQiu0419/GBNet","url":"https://github.com/ShiQiu0419/GBNet"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83475,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"SimpleView","metrics":{"Overall Accuracy":"80.5"},"paper_url":"https://openreview.net/forum?id=XwATtbX3oCz","paper_title":"Revisiting Point Cloud Classification with a Simple and Effective Baseline","paper_date":"2021-01-01","code_links":[{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"IsaacCorley/simpleview-pytorch","url":"https://github.com/IsaacCorley/simpleview-pytorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83476,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DRNet","metrics":{"Mean Accuracy":"78.0","Overall Accuracy":"80.3"},"paper_url":"https://arxiv.org/abs/2005.06734v2","paper_title":"Dense-Resolution Network for Point Cloud Classification and Segmentation","paper_date":"2020-05-14","code_links":[{"title":"ShiQiu0419/DRNet","url":"https://github.com/ShiQiu0419/DRNet"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83477,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointCNN","metrics":{"Mean Accuracy":"75.1","OBJ-BG (OA)":"86.1","OBJ-ONLY (OA)":"85.5","Overall Accuracy":"78.5"},"paper_url":"http://arxiv.org/abs/1801.07791v5","paper_title":"PointCNN: Convolution On $\\mathcal{X}$-Transformed Points","paper_date":"2018-01-23","code_links":[{"title":"pyg-team/pytorch_geometric","url":"https://github.com/pyg-team/pytorch_geometric"},{"title":"yangyanli/PointCNN","url":"https://github.com/yangyanli/PointCNN"},{"title":"luost26/diffusion-point-cloud","url":"https://github.com/luost26/diffusion-point-cloud"},{"title":"nicolas-chaulet/torch-points3d","url":"https://github.com/nicolas-chaulet/torch-points3d"},{"title":"hxdengBerkeley/PointCNN.Pytorch","url":"https://github.com/hxdengBerkeley/PointCNN.Pytorch"},{"title":"octree-nn/ocnn-pytorch","url":"https://github.com/octree-nn/ocnn-pytorch"},{"title":"agarret7/PointCNN","url":"https://github.com/agarret7/PointCNN"},{"title":"chinakook/PointCNN.MX","url":"https://github.com/chinakook/PointCNN.MX"},{"title":"lanlan96/3drm","url":"https://github.com/lanlan96/3drm"},{"title":"NMADALI97/PointCNN_Pytorch","url":"https://github.com/NMADALI97/PointCNN_Pytorch"},{"title":"LebronGG/PointCnn","url":"https://github.com/LebronGG/PointCnn"},{"title":"Lw510107/PointCNN","url":"https://github.com/Lw510107/PointCNN"},{"title":"c3210927/point_cnn","url":"https://github.com/c3210927/point_cnn"},{"title":"tch/pointcnn","url":"https://github.com/tch/pointcnn"},{"title":"dream-chaser/pointcnn_for_3DFER","url":"https://github.com/dream-chaser/pointcnn_for_3DFER"},{"title":"tschattschneider/pointcnn","url":"https://github.com/tschattschneider/pointcnn"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83478,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DGCNN","metrics":{"Mean Accuracy":"73.6","OBJ-BG (OA)":"82.8","OBJ-ONLY (OA)":"86.2","Overall Accuracy":"78.1"},"paper_url":"https://arxiv.org/abs/1801.07829v2","paper_title":"Dynamic Graph CNN for Learning on Point Clouds","paper_date":"2018-01-24","code_links":[{"title":"WangYueFt/dgcnn","url":"https://github.com/WangYueFt/dgcnn"},{"title":"vinits5/learning3d","url":"https://github.com/vinits5/learning3d"},{"title":"AnTao97/dgcnn.pytorch","url":"https://github.com/AnTao97/dgcnn.pytorch"},{"title":"bupt-gamma/gammagl","url":"https://github.com/bupt-gamma/gammagl"},{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"hqucms/ParticleNet","url":"https://github.com/hqucms/ParticleNet"},{"title":"lingzhang1/ContrastNet","url":"https://github.com/lingzhang1/ContrastNet"},{"title":"cy-xu/spatially_aware_ai","url":"https://github.com/cy-xu/spatially_aware_ai"},{"title":"yossilevii100/refocusing","url":"https://github.com/yossilevii100/refocusing"},{"title":"yossilevii100/critical_points2","url":"https://github.com/yossilevii100/critical_points2"},{"title":"hansen7/NRS_3D","url":"https://github.com/hansen7/NRS_3D"},{"title":"brent-murray/tr3d_pointaugdgcnn","url":"https://github.com/brent-murray/tr3d_pointaugdgcnn"},{"title":"nnn911/MLSI","url":"https://github.com/nnn911/MLSI"},{"title":"lingzhang1/dgcnn_sampling","url":"https://github.com/lingzhang1/dgcnn_sampling"},{"title":"lingzhang1/dgcnn_v2","url":"https://github.com/lingzhang1/dgcnn_v2"},{"title":"xrndai/dgcnn_amino_acid_structure","url":"https://github.com/xrndai/dgcnn_amino_acid_structure"},{"title":"JingfeiHuang/DGCNN-Paddle","url":"https://github.com/JingfeiHuang/DGCNN-Paddle"},{"title":"af13s/dgcnn-amino","url":"https://github.com/af13s/dgcnn-amino"},{"title":"Squanch-U/DGCNN","url":"https://github.com/Squanch-U/DGCNN"},{"title":"AmitBracha/GIP_project","url":"https://github.com/AmitBracha/GIP_project"},{"title":"gai-shaoyan/mind3d","url":"https://gitee.com/gai-shaoyan/mind3d"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83479,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNet++","metrics":{"Mean Accuracy":"75.4","OBJ-BG (OA)":"82.3","OBJ-ONLY (OA)":"84.3","Overall Accuracy":"77.9"},"paper_url":"http://arxiv.org/abs/1706.02413v1","paper_title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","paper_date":"2017-06-07","code_links":[{"title":"yanx27/Pointnet_Pointnet2_pytorch","url":"https://github.com/yanx27/Pointnet_Pointnet2_pytorch"},{"title":"charlesq34/pointnet2","url":"https://github.com/charlesq34/pointnet2"},{"title":"facebookresearch/votenet","url":"https://github.com/facebookresearch/votenet"},{"title":"erikwijmans/Pointnet2_PyTorch","url":"https://github.com/erikwijmans/Pointnet2_PyTorch"},{"title":"rusty1s/pytorch_cluster","url":"https://github.com/rusty1s/pytorch_cluster"},{"title":"sshaoshuai/Pointnet2.PyTorch","url":"https://github.com/sshaoshuai/Pointnet2.PyTorch"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/pointnet2"},{"title":"zaiweizhang/H3DNet","url":"https://github.com/zaiweizhang/H3DNet"},{"title":"hehefan/P4Transformer","url":"https://github.com/hehefan/P4Transformer"},{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"thu17cyz/3DIoUMatch","url":"https://github.com/thu17cyz/3DIoUMatch"},{"title":"hehefan/PointRNN","url":"https://github.com/hehefan/PointRNN"},{"title":"facebookresearch/imvotenet","url":"https://github.com/facebookresearch/imvotenet"},{"title":"referit3d/referit3d","url":"https://github.com/referit3d/referit3d"},{"title":"hehefan/Point-Spatio-Temporal-Convolution","url":"https://github.com/hehefan/Point-Spatio-Temporal-Convolution"},{"title":"dgriffiths3/pointnet2-tensorflow2","url":"https://github.com/dgriffiths3/pointnet2-tensorflow2"},{"title":"nickgkan/beauty_detr","url":"https://github.com/nickgkan/beauty_detr"},{"title":"nickgkan/butd_detr","url":"https://github.com/nickgkan/butd_detr"},{"title":"open-air-sun/pq-transformer","url":"https://github.com/open-air-sun/pq-transformer"},{"title":"hehefan/PointRNN-PyTorch","url":"https://github.com/hehefan/PointRNN-PyTorch"},{"title":"joyhsu0504/ns3d","url":"https://github.com/joyhsu0504/ns3d"},{"title":"curryyuan/x-trans2cap","url":"https://github.com/curryyuan/x-trans2cap"},{"title":"zyang-ur/SAT","url":"https://github.com/zyang-ur/SAT"},{"title":"iballester/SPiKE","url":"https://github.com/iballester/SPiKE"},{"title":"johnsonsign/mast-pre","url":"https://github.com/johnsonsign/mast-pre"},{"title":"AsahiLiu/PointDetectron","url":"https://github.com/AsahiLiu/PointDetectron"},{"title":"hehefan/PSTNet2","url":"https://github.com/hehefan/PSTNet2"},{"title":"JohnsonSign/PointCMP","url":"https://github.com/JohnsonSign/PointCMP"},{"title":"dfki-av/mikasa-3dvg","url":"https://github.com/dfki-av/mikasa-3dvg"},{"title":"Ghailen-Ben-Achour/PointNet2_Segmentation","url":"https://github.com/Ghailen-Ben-Achour/PointNet2_Segmentation"},{"title":"houseleo/pointnet","url":"https://github.com/houseleo/pointnet"},{"title":"tao-tao-tao-tao-tao/diffusion_suction","url":"https://github.com/tao-tao-tao-tao-tao/diffusion_suction"},{"title":"Lonepic/SPIB","url":"https://github.com/Lonepic/SPIB"},{"title":"asalarpour/Point_GN","url":"https://github.com/asalarpour/Point_GN"},{"title":"LinZhuoChen/pointnet2_multi_gpu","url":"https://github.com/LinZhuoChen/pointnet2_multi_gpu"},{"title":"shaygu62/Protein-Classification","url":"https://github.com/shaygu62/Protein-Classification"},{"title":"zhh6425/LocalContextPropagation","url":"https://github.com/zhh6425/LocalContextPropagation"},{"title":"ikh-innovation/roboweldar-votenet","url":"https://github.com/ikh-innovation/roboweldar-votenet"},{"title":"witignite/Frustum-PointNet","url":"https://github.com/witignite/Frustum-PointNet"},{"title":"airalcorn2/parking-lot-pointnetplusplus","url":"https://github.com/airalcorn2/parking-lot-pointnetplusplus"},{"title":"ftdlyc/pointnet_pytorch","url":"https://github.com/ftdlyc/pointnet_pytorch"},{"title":"tingxueronghua/dpke","url":"https://github.com/tingxueronghua/dpke"},{"title":"timothylimyl/PointNet-Pytorch","url":"https://github.com/timothylimyl/PointNet-Pytorch"},{"title":"zhh6425/MotionPointNet","url":"https://github.com/zhh6425/MotionPointNet"},{"title":"alililia/ms_extend","url":"https://github.com/alililia/ms_extend/tree/main/ascend_pointnet2"},{"title":"hoangcuongbk80/VoteGrasp","url":"https://github.com/hoangcuongbk80/VoteGrasp"},{"title":"2024-MindSpore-1/Code4","url":"https://github.com/2024-MindSpore-1/Code4/tree/main/PointNet2"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/PointNet2"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/PointNet"},{"title":"alililia/ms_extend","url":"https://github.com/alililia/ms_extend/tree/main/gpu_pointnet2"},{"title":"tonysy/pointnet2_tf","url":"https://github.com/tonysy/pointnet2_tf"},{"title":"Xiangxu-0103/Octant-CNN","url":"https://github.com/Xiangxu-0103/Octant-CNN"},{"title":"Lw510107/PointNet","url":"https://github.com/Lw510107/PointNet"},{"title":"xurui1217/pointnet2-master","url":"https://github.com/xurui1217/pointnet2-master"},{"title":"SY-Xuan/pointnet_plus_plus_paddlepaddle","url":"https://github.com/SY-Xuan/pointnet_plus_plus_paddlepaddle"},{"title":"LONG-9621/VoteNet","url":"https://github.com/LONG-9621/VoteNet"},{"title":"LONG-9621/PointNet-","url":"https://github.com/LONG-9621/PointNet-"},{"title":"Harut0726/votenet","url":"https://github.com/Harut0726/votenet"},{"title":"FlowWind1999/pointnet-2","url":"https://github.com/FlowWind1999/pointnet-2"},{"title":"llzlcl/pointcloud-segment","url":"https://github.com/llzlcl/pointcloud-segment"},{"title":"zenroad/modifypointnet","url":"https://github.com/zenroad/modifypointnet"},{"title":"caizeyu1992/pointnet2","url":"https://github.com/caizeyu1992/pointnet2"},{"title":"2023-MindSpore-1/ms-code-8","url":"https://github.com/2023-MindSpore-1/ms-code-8/tree/main/PointNet2"},{"title":"gai-shaoyan/mind3d","url":"https://gitee.com/gai-shaoyan/mind3d"},{"title":"2023-MindSpore-1/ms-code-223","url":"https://github.com/2023-MindSpore-1/ms-code-223/tree/main/PointNet"},{"title":"MindSpore-paper-code-3/code4","url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/frustum-pointnet"},{"title":"2023-MindSpore-1/ms-code-223","url":"https://github.com/2023-MindSpore-1/ms-code-223/tree/main/PointNet2"},{"title":"brbzjl/pointnet2","url":"https://github.com/brbzjl/pointnet2"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83480,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"SpiderCNN","metrics":{"Mean Accuracy":"69.8","Overall Accuracy":"73.7"},"paper_url":"http://arxiv.org/abs/1803.11527v3","paper_title":"SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters","paper_date":"2018-03-30","code_links":[{"title":"xyf513/SpiderCNN","url":"https://github.com/xyf513/SpiderCNN"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83481,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNet","metrics":{"Mean Accuracy":"63.4","Overall Accuracy":"68.2"},"paper_url":"http://arxiv.org/abs/1612.00593v2","paper_title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","paper_date":"2016-12-02","code_links":[{"title":"charlesq34/pointnet","url":"https://github.com/charlesq34/pointnet"},{"title":"fxia22/pointnet.pytorch","url":"https://github.com/fxia22/pointnet.pytorch"},{"title":"WangYueFt/dgcnn","url":"https://github.com/WangYueFt/dgcnn"},{"title":"vinits5/learning3d","url":"https://github.com/vinits5/learning3d"},{"title":"DylanWusee/pointconv_pytorch","url":"https://github.com/DylanWusee/pointconv_pytorch"},{"title":"nikitakaraevv/pointnet","url":"https://github.com/nikitakaraevv/pointnet"},{"title":"maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification","url":"https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification"},{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"sarthakTUM/roofn3d","url":"https://github.com/sarthakTUM/roofn3d"},{"title":"jtpils/treegan","url":"https://github.com/jtpils/treegan"},{"title":"ajhamdi/AdvPC","url":"https://github.com/ajhamdi/AdvPC"},{"title":"soumik12345/point-cloud-segmentation","url":"https://github.com/soumik12345/point-cloud-segmentation"},{"title":"AI-Guru/pointcloud_experiments","url":"https://github.com/AI-Guru/pointcloud_experiments"},{"title":"ali-stanford/pointnetcfd","url":"https://github.com/ali-stanford/pointnetcfd"},{"title":"romaintha/pytorch_pointnet","url":"https://github.com/romaintha/pytorch_pointnet"},{"title":"saaries/PointNet","url":"https://github.com/saaries/PointNet"},{"title":"Fragjacker/Pointcloud-grad-CAM","url":"https://github.com/Fragjacker/Pointcloud-grad-CAM"},{"title":"ZhihaoZhu/PointNet-Implementation-Tensorflow","url":"https://github.com/ZhihaoZhu/PointNet-Implementation-Tensorflow"},{"title":"YanWei123/Pytorch-implementation-of-FoldingNet-encoder-and-decoder-with-graph-pooling-covariance-add-quanti","url":"https://github.com/YanWei123/Pytorch-implementation-of-FoldingNet-encoder-and-decoder-with-graph-pooling-covariance-add-quanti"},{"title":"Yuto0107/pointnet","url":"https://github.com/Yuto0107/pointnet"},{"title":"YanWei123/PointNet-encoder-and-FoldingNet-decoder-add-quantization-change-latent-code-size-from-512-to-1024","url":"https://github.com/YanWei123/PointNet-encoder-and-FoldingNet-decoder-add-quantization-change-latent-code-size-from-512-to-1024"},{"title":"opeco17/pointnet","url":"https://github.com/opeco17/pointnet"},{"title":"Dir-b/PointNet","url":"https://github.com/Dir-b/PointNet"},{"title":"Young98CN/pointconv_pytorch","url":"https://github.com/Young98CN/pointconv_pytorch"},{"title":"y2kmz/pointnetv2","url":"https://github.com/y2kmz/pointnetv2"},{"title":"YanWei123/Pointnet_encoder_Foldingnet_decoder_quantization","url":"https://github.com/YanWei123/Pointnet_encoder_Foldingnet_decoder_quantization"},{"title":"imanlab/deep_movement_primitives","url":"https://github.com/imanlab/deep_movement_primitives"},{"title":"abdullahozer11/Segmentation-and-Classification-of-Objects-in-Point-Clouds","url":"https://github.com/abdullahozer11/Segmentation-and-Classification-of-Objects-in-Point-Clouds"},{"title":"donshen/pointnet.phasedetection","url":"https://github.com/donshen/pointnet.phasedetection"},{"title":"ModelBunker/PointNet-TensorFlow","url":"https://github.com/ModelBunker/PointNet-TensorFlow"},{"title":"amyllykoski/CycleGAN","url":"https://github.com/amyllykoski/CycleGAN"},{"title":"Javed002/Object_detection_PointNet","url":"https://github.com/Javed002/Object_detection_PointNet"},{"title":"sanantoniochili/PointCloud_KNN","url":"https://github.com/sanantoniochili/PointCloud_KNN"},{"title":"PaParaZz1/PointNet","url":"https://github.com/PaParaZz1/PointNet"},{"title":"yevgm/deepadv3d","url":"https://github.com/yevgm/deepadv3d"},{"title":"witignite/Frustum-PointNet","url":"https://github.com/witignite/Frustum-PointNet"},{"title":"m-117/PointNet-ein-Implementationsbeispiel-mit-Jupyter-Notebooks","url":"https://github.com/m-117/PointNet-ein-Implementationsbeispiel-mit-Jupyter-Notebooks"},{"title":"alpemek/ais3d","url":"https://github.com/alpemek/ais3d"},{"title":"yanxp/PointNet","url":"https://github.com/yanxp/PointNet"},{"title":"ftdlyc/pointnet_pytorch","url":"https://github.com/ftdlyc/pointnet_pytorch"},{"title":"Melo-Wang/Deep-Learning-on-Point-Cloud-of-Aerospace-Components-for-3D-Classification","url":"https://github.com/Melo-Wang/Deep-Learning-on-Point-Cloud-of-Aerospace-Components-for-3D-Classification"},{"title":"Phimos/Paddle-PointNet","url":"https://github.com/Phimos/Paddle-PointNet"},{"title":"zgx0534/pointnet_win","url":"https://github.com/zgx0534/pointnet_win"},{"title":"timothylimyl/PointNet-Pytorch","url":"https://github.com/timothylimyl/PointNet-Pytorch"},{"title":"minhncedutw/pointnet1_keras","url":"https://github.com/minhncedutw/pointnet1_keras"},{"title":"Jagyan/ghost_radarpoint_detection","url":"https://github.com/Jagyan/ghost_radarpoint_detection"},{"title":"brendanmallery9/entropic-barycenters","url":"https://github.com/brendanmallery9/entropic-barycenters"},{"title":"2024-MindSpore-1/Code4","url":"https://github.com/2024-MindSpore-1/Code4/tree/main/PointNet"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/frustum-pointnet"},{"title":"xiuyu0000/vision","url":"https://github.com/xiuyu0000/vision/blob/main/mindvision/ms3d/models/pointnet2cls.py"},{"title":"hnmspirit/pointnet1","url":"https://github.com/hnmspirit/pointnet1"},{"title":"yangyucheng000/pointnet","url":"https://github.com/yangyucheng000/pointnet"},{"title":"eth212/Qmind_ModelNet10_PointNet","url":"https://github.com/eth212/Qmind_ModelNet10_PointNet"},{"title":"smfirmin/DeepLearningFinalProject","url":"https://github.com/smfirmin/DeepLearningFinalProject"},{"title":"ECE685-FinalProject/3D-object-recognition","url":"https://github.com/ECE685-FinalProject/3D-object-recognition"},{"title":"KhusDM/PointNetTree","url":"https://github.com/KhusDM/PointNetTree"},{"title":"Lw510107/pointnet-2018.6.27-","url":"https://github.com/Lw510107/pointnet-2018.6.27-"},{"title":"xurui1217/pointnet.pytorch-master","url":"https://github.com/xurui1217/pointnet.pytorch-master"},{"title":"hnVfly/pointnet.mxnet","url":"https://github.com/hnVfly/pointnet.mxnet"},{"title":"LebronGG/PointNet","url":"https://github.com/LebronGG/PointNet"},{"title":"GOD-GOD-Autonomous-Vehicle/self-pointnet","url":"https://github.com/GOD-GOD-Autonomous-Vehicle/self-pointnet"},{"title":"AlfredoZermini/PointNet","url":"https://github.com/AlfredoZermini/PointNet"},{"title":"wonderland-dsg/pointnet-grid","url":"https://github.com/wonderland-dsg/pointnet-grid"},{"title":"aviros/roatationPointnet","url":"https://github.com/aviros/roatationPointnet"},{"title":"THHHomas/mls","url":"https://github.com/THHHomas/mls"},{"title":"liuch37/pointnet","url":"https://github.com/liuch37/pointnet"},{"title":"yanx27/Pointnet","url":"https://github.com/yanx27/Pointnet"},{"title":"Taeuk-Jang/pointcompletion","url":"https://github.com/Taeuk-Jang/pointcompletion"},{"title":"ytng001/sensemaking","url":"https://github.com/ytng001/sensemaking"},{"title":"nddoshi/pointnet","url":"https://github.com/nddoshi/pointnet"},{"title":"SY-Xuan/pointnet_paddle","url":"https://github.com/SY-Xuan/pointnet_paddle"},{"title":"Cmeijiang/PointNet_MS","url":"https://github.com/Cmeijiang/PointNet_MS"},{"title":"AndreiMoraru123/PointNet","url":"https://github.com/AndreiMoraru123/PointNet"},{"title":"mengxingshifen1218/pointnet.pytorch","url":"https://github.com/mengxingshifen1218/pointnet.pytorch"},{"title":"Moon-Xuezha/PointNet","url":"https://github.com/Moon-Xuezha/PointNet"},{"title":"ajertec/PointNetKeras","url":"https://github.com/ajertec/PointNetKeras"},{"title":"2023-MindSpore-1/ms-code-35","url":"https://github.com/2023-MindSpore-1/ms-code-35"},{"title":"LONG-9621/Extract_Point_3D","url":"https://github.com/LONG-9621/Extract_Point_3D"},{"title":"Mind23-2/MindCode-63","url":"https://github.com/Mind23-2/MindCode-63"},{"title":"merazlab/3D_Deep_Learning_Link","url":"https://github.com/merazlab/3D_Deep_Learning_Link"},{"title":"2023-MindSpore-1/ms-code-7","url":"https://github.com/2023-MindSpore-1/ms-code-7/tree/main/PointNet"},{"title":"KaidongLi/tf-3d-alpha","url":"https://github.com/KaidongLi/tf-3d-alpha"},{"title":"gai-shaoyan/mind3d","url":"https://gitee.com/gai-shaoyan/mind3d"},{"title":"prasadsawant5/PointNet","url":"https://github.com/prasadsawant5/PointNet"},{"title":"SonuDileep/3-D-Object-Detection-using-PointNet","url":"https://github.com/SonuDileep/3-D-Object-Detection-using-PointNet"},{"title":"BPMJG/annotated_pointnet","url":"https://github.com/BPMJG/annotated_pointnet"},{"title":"debajyotid2/pointnet_pl","url":"https://github.com/debajyotid2/pointnet_pl"},{"title":"SBPL-Cruz/perch_pose_sampler","url":"https://github.com/SBPL-Cruz/perch_pose_sampler"},{"title":"2023-MindSpore-4/Code9","url":"https://github.com/2023-MindSpore-4/Code9/tree/main/PointNet"},{"title":"wuryantoAji/POINTNET","url":"https://github.com/wuryantoAji/POINTNET"},{"title":"LONG-9621/PointNet","url":"https://github.com/LONG-9621/PointNet"},{"title":"bt77/pointnet","url":"https://github.com/bt77/pointnet"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/PointNet2"},{"title":"KiranAkadas/My_Pointnet_v2","url":"https://github.com/KiranAkadas/My_Pointnet_v2"},{"title":"YiruS/pointnet_adversarial","url":"https://github.com/YiruS/pointnet_adversarial"},{"title":"Harut0726/my-pointnet-tensorflow","url":"https://github.com/Harut0726/my-pointnet-tensorflow"},{"title":"AlvesRobot/Deep-Learning-on-Point-Cloud-for-3D-Classification-and-Segmentation","url":"https://github.com/AlvesRobot/Deep-Learning-on-Point-Cloud-for-3D-Classification-and-Segmentation"},{"title":"hz-ants/pointnet.pytorch","url":"https://github.com/hz-ants/pointnet.pytorch"},{"title":"VaanHUANG/CSCI5210HW1","url":"https://github.com/VaanHUANG/CSCI5210HW1"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/PointNet"},{"title":"ShadowShadowWong/update-pointnet-work","url":"https://github.com/ShadowShadowWong/update-pointnet-work"},{"title":"Yang2446/pointnet","url":"https://github.com/Yang2446/pointnet"},{"title":"lingzhang1/pointnet_pytorch","url":"https://github.com/lingzhang1/pointnet_pytorch"},{"title":"dwtstore/sfm1","url":"https://github.com/dwtstore/sfm1"},{"title":"freddieee/pn_6d_single","url":"https://github.com/freddieee/pn_6d_single"},{"title":"ahmed-anas/thesis-pointnet","url":"https://github.com/ahmed-anas/thesis-pointnet"},{"title":"coconutzs/PointNet_zs","url":"https://github.com/coconutzs/PointNet_zs"},{"title":"CheesyB/cpointnet","url":"https://github.com/CheesyB/cpointnet"},{"title":"lingzhang1/pointnet_tensorflow","url":"https://github.com/lingzhang1/pointnet_tensorflow"},{"title":"aviros/pointnet_totations","url":"https://github.com/aviros/pointnet_totations"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":83482,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ExpPoint-MAE","metrics":{"OBJ-BG (OA)":"90.88","OBJ-ONLY (OA)":"90.02"},"paper_url":"https://arxiv.org/abs/2306.10798v3","paper_title":"ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformers","paper_date":"2023-06-19","code_links":[{"title":"vvrpanda/exppoint-mae","url":"https://github.com/vvrpanda/exppoint-mae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105887,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"OmniVec2","metrics":{"Overall Accuracy":"97.2"},"paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Srivastava_OmniVec2_-_A_Novel_Transformer_based_Network_for_Large_Scale_CVPR_2024_paper.html","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","paper_date":"2024-01-01","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105888,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointGST","metrics":{"OBJ-BG (OA)":"99.48","OBJ-ONLY (OA)":"97.76","Overall Accuracy":"96.18"},"paper_url":"https://arxiv.org/abs/2410.08114v1","paper_title":"Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning","paper_date":"2024-10-10","code_links":[{"title":"jerryfeng2003/pointgst","url":"https://github.com/jerryfeng2003/pointgst"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105889,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"OmniVec","metrics":{"Overall Accuracy":"96.1"},"paper_url":"https://arxiv.org/abs/2311.05709v1","paper_title":"OmniVec: Learning robust representations with cross modal sharing","paper_date":"2023-11-07","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105890,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"GPSFormer","metrics":{"FLOPs":"0.7G","Mean Accuracy":"93.8","Number of params":"2.36M","Overall Accuracy":"95.4"},"paper_url":"https://arxiv.org/abs/2407.13519v2","paper_title":"GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding","paper_date":"2024-07-18","code_links":[{"title":"changshuowang/GPSFormer","url":"https://github.com/changshuowang/GPSFormer"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105891,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ReCon++","metrics":{"OBJ-BG (OA)":"98.80","OBJ-ONLY (OA)":"97.59","Overall Accuracy":"95.25"},"paper_url":"https://arxiv.org/abs/2402.17766v3","paper_title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","paper_date":"2024-02-27","code_links":[{"title":"qizekun/ShapeLLM","url":"https://github.com/qizekun/ShapeLLM"},{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105892,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"AsymDSD-B* (no voting)","metrics":{"OBJ-BG (OA)":"96.73","OBJ-ONLY (OA)":"94.32","Overall Accuracy":"93.72"},"paper_url":"https://arxiv.org/abs/2506.21724v1","paper_title":"Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning","paper_date":"2025-06-26","code_links":[{"title":"RFLeijenaar/AsymDSD","url":"https://github.com/RFLeijenaar/AsymDSD"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105893,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointGPT","metrics":{"OBJ-BG (OA)":"97.2","OBJ-ONLY (OA)":"96.6","Overall Accuracy":"93.4"},"paper_url":"https://arxiv.org/abs/2305.11487v2","paper_title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","paper_date":"2023-05-19","code_links":[{"title":"CGuangyan-BIT/PointGPT","url":"https://github.com/CGuangyan-BIT/PointGPT"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105894,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"GPSFormer-elite","metrics":{"Mean Accuracy":"92.51","Number of params":"0.68M","Overall Accuracy":"93.30"},"paper_url":"https://arxiv.org/abs/2407.13519v2","paper_title":"GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding","paper_date":"2024-07-18","code_links":[{"title":"changshuowang/GPSFormer","url":"https://github.com/changshuowang/GPSFormer"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105895,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Mamba3D","metrics":{"FLOPs":"3.9G","Number of params":"16.9M","OBJ-BG (OA)":"94.49","OBJ-ONLY (OA)":"92.43","Overall Accuracy":"92.64"},"paper_url":"https://arxiv.org/abs/2404.14966v2","paper_title":"Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model","paper_date":"2024-04-23","code_links":[{"title":"xhanxu/Mamba3D","url":"https://github.com/xhanxu/Mamba3D"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105896,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Mamba3D (no voting)","metrics":{"FLOPs":"3.9G","Number of params":"16.9M","OBJ-BG (OA)":"92.94","OBJ-ONLY (OA)":"92.08","Overall Accuracy":"91.81"},"paper_url":"https://arxiv.org/abs/2404.14966v2","paper_title":"Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model","paper_date":"2024-04-23","code_links":[{"title":"xhanxu/Mamba3D","url":"https://github.com/xhanxu/Mamba3D"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105897,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ULIP-2 + PointNeXt","metrics":{"Mean Accuracy":"91.2","Number of params":"1.4M","Overall Accuracy":"91.5"},"paper_url":"https://arxiv.org/abs/2305.08275v4","paper_title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","paper_date":"2023-05-14","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105898,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ReCon","metrics":{"OBJ-BG (OA)":"95.35","OBJ-ONLY (OA)":"93.80","Overall Accuracy":"91.26"},"paper_url":"https://arxiv.org/abs/2302.02318v2","paper_title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","paper_date":"2023-02-05","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"aHapBean/PCP-MAE","url":"https://github.com/aHapBean/PCP-MAE"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105899,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ULIP-2 + PointNeXt (no voting)","metrics":{"Mean Accuracy":"90.3","Number of params":"1.4M","Overall Accuracy":"90.8"},"paper_url":"https://arxiv.org/abs/2305.08275v4","paper_title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","paper_date":"2023-05-14","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105900,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ReCon (no voting)","metrics":{"OBJ-BG (OA)":"95.18","OBJ-ONLY (OA)":"93.29","Overall Accuracy":"90.63"},"paper_url":"https://arxiv.org/abs/2302.02318v2","paper_title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","paper_date":"2023-02-05","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"aHapBean/PCP-MAE","url":"https://github.com/aHapBean/PCP-MAE"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105901,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"AsymDSD-S (no voting)","metrics":{"OBJ-BG (OA)":"94.32","OBJ-ONLY (OA)":"91.91","Overall Accuracy":"90.53"},"paper_url":"https://arxiv.org/abs/2506.21724v1","paper_title":"Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning","paper_date":"2025-06-26","code_links":[{"title":"RFLeijenaar/AsymDSD","url":"https://github.com/RFLeijenaar/AsymDSD"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105902,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"DeLA","metrics":{"FLOPs":"1.5G","Mean Accuracy":"89.3","Number of params":"5.3M","Overall Accuracy":"90.4"},"paper_url":"https://arxiv.org/abs/2308.16532v1","paper_title":"Decoupled Local Aggregation for Point Cloud Learning","paper_date":"2023-08-31","code_links":[{"title":"matrix-asc/dela","url":"https://github.com/matrix-asc/dela"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105903,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PCP-MAE","metrics":{"OBJ-BG (OA)":"95.52","OBJ-ONLY (OA)":"94.32","Overall Accuracy":"90.35"},"paper_url":"https://arxiv.org/abs/2408.08753v2","paper_title":"PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders","paper_date":"2024-08-16","code_links":[{"title":"aHapBean/PCP-MAE","url":"https://github.com/aHapBean/PCP-MAE"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105904,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointConT","metrics":{"Mean Accuracy":"88.5","Overall Accuracy":"90.3"},"paper_url":"https://arxiv.org/abs/2303.04599v1","paper_title":"Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space","paper_date":"2023-03-08","code_links":[{"title":"yahuiliu99/pointcont","url":"https://github.com/yahuiliu99/pointcont"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105905,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Point-RAE (no voting)","metrics":{"OBJ-BG (OA)":"95.53","OBJ-ONLY (OA)":"93.63","Overall Accuracy":"90.28"},"paper_url":"https://arxiv.org/abs/2310.03670v1","paper_title":"Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning","paper_date":"2023-09-25","code_links":[{"title":"liuyyy111/point-rae","url":"https://github.com/liuyyy111/point-rae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105906,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Point-FEMAE","metrics":{"OBJ-BG (OA)":"95.18","OBJ-ONLY (OA)":"93.29","Overall Accuracy":"90.22"},"paper_url":"https://arxiv.org/abs/2312.10726v1","paper_title":"Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders","paper_date":"2023-12-17","code_links":[{"title":"zyh16143998882/aaai24-pointfemae","url":"https://github.com/zyh16143998882/aaai24-pointfemae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105907,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"I2P-MAE (no voting)","metrics":{"OBJ-BG (OA)":"94.15","OBJ-ONLY (OA)":"91.57","Overall Accuracy":"90.11"},"paper_url":"https://arxiv.org/abs/2212.06785v1","paper_title":"Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders","paper_date":"2022-12-13","code_links":[{"title":"zrrskywalker/i2p-mae","url":"https://github.com/zrrskywalker/i2p-mae"},{"title":"zrrskywalker/point-m2ae","url":"https://github.com/zrrskywalker/point-m2ae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105908,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ULIP + PointNeXt","metrics":{"Mean Accuracy":"88.6","Number of params":"1.4M","Overall Accuracy":"89.7"},"paper_url":"https://arxiv.org/abs/2212.05171v4","paper_title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","paper_date":"2022-12-10","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105909,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ReCon+PPT","metrics":{"OBJ-BG (OA)":"95.01","OBJ-ONLY (OA)":"93.28","Overall Accuracy":"89.52"},"paper_url":"https://arxiv.org/abs/2408.11567v1","paper_title":"Positional Prompt Tuning for Efficient 3D Representation Learning","paper_date":"2024-08-21","code_links":[{"title":"zsc000722/ppt","url":"https://github.com/zsc000722/ppt"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105910,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"3D-JEPA","metrics":{"OBJ-BG (OA)":"93.63","OBJ-ONLY (OA)":"94.49","Overall Accuracy":"89.52"},"paper_url":"https://arxiv.org/abs/2409.15803v1","paper_title":"3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning","paper_date":"2024-09-24","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105911,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointMLP∗ + JM3D","metrics":{"Mean Accuracy":"88.7","Overall Accuracy":"89.5"},"paper_url":"https://arxiv.org/abs/2308.02982v2","paper_title":"Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation","paper_date":"2023-08-06","code_links":[{"title":"mr-neko/jm3d","url":"https://github.com/mr-neko/jm3d"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105912,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ULIP + PointMLP","metrics":{"Mean Accuracy":"88.5","Overall Accuracy":"89.4"},"paper_url":"https://arxiv.org/abs/2212.05171v4","paper_title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","paper_date":"2022-12-10","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105913,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"KPConvX-L","metrics":{"Mean Accuracy":"88.1","Overall Accuracy":"89.3"},"paper_url":"https://arxiv.org/abs/2405.13194v1","paper_title":"KPConvX: Modernizing Kernel Point Convolution with Kernel Attention","paper_date":"2024-05-21","code_links":[{"title":"apple/ml-kpconvx","url":"https://github.com/apple/ml-kpconvx"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105914,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"P2P","metrics":{"Number of params":"195.8M","Overall Accuracy":"89.3"},"paper_url":"https://arxiv.org/abs/2208.02812v2","paper_title":"P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting","paper_date":"2022-08-04","code_links":[{"title":"wangzy22/P2P","url":"https://github.com/wangzy22/P2P"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105915,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ACT","metrics":{"Overall Accuracy":"89.17"},"paper_url":"https://arxiv.org/abs/2212.08320v2","paper_title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","paper_date":"2022-12-16","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105916,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Ours","metrics":{"Mean Accuracy":"87.2","Overall Accuracy":"89.0"},"paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320324004631","paper_title":"Beyond local patches: Preserving global–local interactions by enhancing self-attention via 3D point cloud tokenization","paper_date":"2024-11-01","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105917,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"OTMae3D","metrics":{"FLOPs":"6.29","OBJ-BG (OA)":"92.9","OBJ-ONLY (OA)":"92.3","Overall Accuracy":"89.0"},"paper_url":"https://ieeexplore.ieee.org/document/10815033","paper_title":"Rethinking Masked Representation Learning for 3D Point Cloud Understanding","paper_date":"2024-12-26","code_links":[{"title":"OpenSpaceAI/OTMae3D","url":"https://github.com/OpenSpaceAI/OTMae3D"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105918,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ULIP-2 + Point-BERT","metrics":{"Overall Accuracy":"89.0"},"paper_url":"https://arxiv.org/abs/2305.08275v4","paper_title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","paper_date":"2023-05-14","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105919,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointNeXt+Local","metrics":{"Mean Accuracy":"87.4","Overall Accuracy":"88.6"},"paper_url":"https://arxiv.org/abs/2212.05140v2","paper_title":"Local Neighborhood Features for 3D Classification","paper_date":"2022-12-09","code_links":[{"title":"VimsLab/Local3DFeatures","url":"https://github.com/VimsLab/Local3DFeatures"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105920,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"SPoTr","metrics":{"Mean Accuracy":"86.8","Overall Accuracy":"88.6"},"paper_url":"https://arxiv.org/abs/2303.16450v1","paper_title":"Self-positioning Point-based Transformer for Point Cloud Understanding","paper_date":"2023-03-29","code_links":[{"title":"mlvlab/spotr","url":"https://github.com/mlvlab/spotr"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105921,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"IDPT","metrics":{"OBJ-BG (OA)":"93.12","Overall Accuracy":"88.51"},"paper_url":"https://arxiv.org/abs/2304.07221v2","paper_title":"Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models","paper_date":"2023-04-14","code_links":[{"title":"zyh16143998882/iccv23-idpt","url":"https://github.com/zyh16143998882/iccv23-idpt"},{"title":"zyh16143998882/IDPT","url":"https://github.com/zyh16143998882/IDPT"},{"title":"zyh16143998882/aaai24-pointfemae","url":"https://github.com/zyh16143998882/aaai24-pointfemae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105922,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointMLP+TAP","metrics":{"Overall Accuracy":"88.5"},"paper_url":"https://arxiv.org/abs/2307.14971v2","paper_title":"Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models","paper_date":"2023-07-27","code_links":[{"title":"wangzy22/tap","url":"https://github.com/wangzy22/tap"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105923,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointNeXt+GAM","metrics":{"FLOPs":"1.64G","Number of params":"1.4M","Overall Accuracy":"88.4"},"paper_url":"http://arxiv.org/abs/1505.07110v2","paper_title":"$(0, 4)$ dualities","paper_date":"2015-12-14","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105924,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointNeXt+HyCoRe","metrics":{"Mean Accuracy":"87.0","Overall Accuracy":"88.3"},"paper_url":"https://arxiv.org/abs/2209.10318v1","paper_title":"Rethinking the compositionality of point clouds through regularization in the hyperbolic space","paper_date":"2022-09-21","code_links":[{"title":"diegovalsesia/hycore","url":"https://github.com/diegovalsesia/hycore"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105925,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ACT (no voting)","metrics":{"OBJ-BG (OA)":"93.29","OBJ-ONLY (OA)":"91.91","Overall Accuracy":"88.21"},"paper_url":"https://arxiv.org/abs/2212.08320v2","paper_title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","paper_date":"2022-12-16","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105926,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointNeXt","metrics":{"FLOPs":"1.64G","Mean Accuracy":"86.8","Number of params":"1.4M","Overall Accuracy":"88.2"},"paper_url":"https://arxiv.org/abs/2206.04670v2","paper_title":"PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies","paper_date":"2022-06-09","code_links":[{"title":"guochengqian/pointnext","url":"https://github.com/guochengqian/pointnext"},{"title":"linhaojia13/pointmetabase","url":"https://github.com/linhaojia13/pointmetabase"},{"title":"boyden/pointtransformerfl","url":"https://github.com/boyden/pointtransformerfl"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105927,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointConT (no voting)","metrics":{"Mean Accuracy":"86.0","Overall Accuracy":"88.0"},"paper_url":"https://arxiv.org/abs/2303.04599v1","paper_title":"Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space","paper_date":"2023-03-08","code_links":[{"title":"yahuiliu99/pointcont","url":"https://github.com/yahuiliu99/pointcont"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105928,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointVector-S","metrics":{"Mean Accuracy":"86.2","Overall Accuracy":"87.8"},"paper_url":"https://arxiv.org/abs/2205.10528v3","paper_title":"PointVector: A Vector Representation In Point Cloud Analysis","paper_date":"2022-05-21","code_links":[{"title":"guochengqian/openpoints","url":"https://github.com/guochengqian/openpoints/blob/master/models/backbone/pointvector.py"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105929,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"point2vec","metrics":{"Mean Accuracy":"86.0","OBJ-BG (OA)":"91.2","OBJ-ONLY (OA)":"90.4","Overall Accuracy":"87.5"},"paper_url":"https://arxiv.org/abs/2303.16570v2","paper_title":"Point2Vec for Self-Supervised Representation Learning on Point Clouds","paper_date":"2023-03-29","code_links":[{"title":"kabouzeid/point2vec","url":"https://github.com/kabouzeid/point2vec"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105930,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointStack","metrics":{"Mean Accuracy":"86.2","Overall Accuracy":"87.2"},"paper_url":"https://arxiv.org/abs/2205.09962v1","paper_title":"Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling","paper_date":"2022-05-20","code_links":[{"title":"LongerVision/PointStack","url":"https://github.com/LongerVision/PointStack"},{"title":"kaist-avelab/PointStack","url":"https://github.com/kaist-avelab/PointStack"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105931,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Point-PN","metrics":{"Number of params":"0.8M","Overall Accuracy":"87.1"},"paper_url":"https://arxiv.org/abs/2303.08134v2","paper_title":"Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis","paper_date":"2023-03-14","code_links":[{"title":"zrrskywalker/point-nn","url":"https://github.com/zrrskywalker/point-nn"},{"title":"opengvlab/cafo","url":"https://github.com/opengvlab/cafo"},{"title":"asalarpour/Point_GN","url":"https://github.com/asalarpour/Point_GN"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105932,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointCMT","metrics":{"Mean Accuracy":"84.8","Number of params":"12.6M","Overall Accuracy":"86.7"},"paper_url":"https://arxiv.org/abs/2210.04208v1","paper_title":"Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis","paper_date":"2022-10-09","code_links":[{"title":"yanx27/2dpass","url":"https://github.com/yanx27/2dpass"},{"title":"zhanheshen/pointcmt","url":"https://github.com/zhanheshen/pointcmt"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105933,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Point-JEPA","metrics":{"OBJ-BG (OA)":"92.9±0.4","Overall Accuracy":"86.6"},"paper_url":"https://arxiv.org/abs/2404.16432v5","paper_title":"Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud","paper_date":"2024-04-25","code_links":[{"title":"Ayumu-J-S/Point-JEPA","url":"https://github.com/Ayumu-J-S/Point-JEPA"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105934,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointMLS","metrics":{"Overall Accuracy":"86.6"},"paper_url":"https://arxiv.org/abs/2401.08210v1","paper_title":"ModelNet-O: A Large-Scale Synthetic Dataset for Occlusion-Aware Point Cloud Classification","paper_date":"2024-01-16","code_links":[{"title":"fanglaosi/pointmls","url":"https://github.com/fanglaosi/pointmls"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105935,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Point-M2AE","metrics":{"OBJ-BG (OA)":"91.22","OBJ-ONLY (OA)":"88.81","Overall Accuracy":"86.43"},"paper_url":"https://arxiv.org/abs/2205.14401v2","paper_title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","paper_date":"2022-05-28","code_links":[{"title":"zrrskywalker/i2p-mae","url":"https://github.com/zrrskywalker/i2p-mae"},{"title":"zrrskywalker/point-m2ae","url":"https://github.com/zrrskywalker/point-m2ae"},{"title":"MindSpore-paper-code-2/code400","url":"https://github.com/MindSpore-paper-code-2/code400/tree/main/MAE"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105936,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ULIP + PointBERT","metrics":{"Overall Accuracy":"86.4"},"paper_url":"https://arxiv.org/abs/2212.05171v4","paper_title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","paper_date":"2022-12-10","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105937,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"DualMLP","metrics":{"Overall Accuracy":"86.4"},"paper_url":"https://link.springer.com/article/10.1007/s00371-023-03114-3","paper_title":"DualMLP: a two-stream fusion model for 3D point cloud classification","paper_date":"2023-10-10","code_links":[{"title":"snehaputul/DualMLP","url":"https://github.com/snehaputul/DualMLP"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105938,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"RepSurf-U (2x)","metrics":{"FLOPs":"2.43G","Number of params":"6.80M","Overall Accuracy":"86.0"},"paper_url":"https://arxiv.org/abs/2205.05740v2","paper_title":"Surface Representation for Point Clouds","paper_date":"2022-05-11","code_links":[{"title":"hancyran/RepSurf","url":"https://github.com/hancyran/RepSurf"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105939,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointMLP","metrics":{"Mean Accuracy":"84.4","Overall Accuracy":"85.7"},"paper_url":"https://arxiv.org/abs/2202.07123v2","paper_title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","paper_date":"2022-02-15","code_links":[{"title":"ma-xu/pointmlp-pytorch","url":"https://github.com/ma-xu/pointmlp-pytorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105940,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Point-LGMask","metrics":{"OBJ-BG (OA)":"89.8","OBJ-ONLY (OA)":"89.3","Overall Accuracy":"85.3"},"paper_url":"https://ieeexplore.ieee.org/abstract/document/10146493","paper_title":"Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking","paper_date":"2023-06-08","code_links":[{"title":"TangYuan96/Point-LGMask","url":"https://github.com/TangYuan96/Point-LGMask"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105941,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Point-MAE","metrics":{"OBJ-BG (OA)":"90.02","OBJ-ONLY (OA)":"88.29","Overall Accuracy":"85.2"},"paper_url":"https://arxiv.org/abs/2203.06604v2","paper_title":"Masked Autoencoders for Point Cloud Self-supervised Learning","paper_date":"2022-03-13","code_links":[{"title":"Pang-Yatian/Point-MAE","url":"https://github.com/Pang-Yatian/Point-MAE"},{"title":"lmd0311/pointmamba","url":"https://github.com/lmd0311/pointmamba"},{"title":"vvrpanda/exppoint-mae","url":"https://github.com/vvrpanda/exppoint-mae"},{"title":"liujia99/tpm","url":"https://github.com/liujia99/tpm"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105942,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"MVTN+SimpleView++","metrics":{"Overall Accuracy":"84.8"},"paper_url":"https://ieeexplore.ieee.org/document/9874679","paper_title":"SimpleView++: Neighborhood Views for Point Cloud Classification","paper_date":"2022-09-08","code_links":[{"title":"VimsLab/SimpleViewPlusPlus","url":"https://github.com/VimsLab/SimpleViewPlusPlus"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105943,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"DeltaConv","metrics":{"Overall Accuracy":"84.7"},"paper_url":"https://arxiv.org/abs/2111.08799v5","paper_title":"DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds","paper_date":"2021-11-16","code_links":[{"title":"rubenwiersma/deltaconv","url":"https://github.com/rubenwiersma/deltaconv"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105944,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"RepSurf-U","metrics":{"FLOPs":"0.81G","Number of params":"1.48M","Overall Accuracy":"84.6"},"paper_url":"https://arxiv.org/abs/2205.05740v2","paper_title":"Surface Representation for Point Clouds","paper_date":"2022-05-11","code_links":[{"title":"hancyran/RepSurf","url":"https://github.com/hancyran/RepSurf"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105945,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"APP-Net","metrics":{"Overall Accuracy":"84.1"},"paper_url":"https://arxiv.org/abs/2205.00847v2","paper_title":"APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification","paper_date":"2022-05-02","code_links":[{"title":"mcg-nju/app-net","url":"https://github.com/mcg-nju/app-net"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105946,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointMLP-elite","metrics":{"Mean Accuracy":"81.8","Overall Accuracy":" 83.8"},"paper_url":"https://arxiv.org/abs/2202.07123v2","paper_title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","paper_date":"2022-02-15","code_links":[{"title":"ma-xu/pointmlp-pytorch","url":"https://github.com/ma-xu/pointmlp-pytorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105947,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointNet++ + SageMix","metrics":{"Overall Accuracy":"83.7"},"paper_url":"https://arxiv.org/abs/2210.06944v1","paper_title":"SageMix: Saliency-Guided Mixup for Point Clouds","paper_date":"2022-10-13","code_links":[{"title":"mlvlab/SageMix","url":"https://github.com/mlvlab/SageMix"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105948,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"DGCNN + SageMix","metrics":{"Overall Accuracy":"83.6"},"paper_url":"https://arxiv.org/abs/2210.06944v1","paper_title":"SageMix: Saliency-Guided Mixup for Point Clouds","paper_date":"2022-10-13","code_links":[{"title":"mlvlab/SageMix","url":"https://github.com/mlvlab/SageMix"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105949,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Point-TnT","metrics":{"FLOPs":"1.19G","Mean Accuracy":"81.0","Number of params":"3.9M","Overall Accuracy":"83.5"},"paper_url":"https://arxiv.org/abs/2204.03957v1","paper_title":"Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition","paper_date":"2022-04-08","code_links":[{"title":"axeber01/point-tnt","url":"https://github.com/axeber01/point-tnt"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105950,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"Point-BERT","metrics":{"OBJ-BG (OA)":"87.43","OBJ-ONLY (OA)":"88.12","Overall Accuracy":"83.1"},"paper_url":"https://arxiv.org/abs/2111.14819v2","paper_title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","paper_date":"2021-11-29","code_links":[{"title":"julie-tang00/point-bert","url":"https://github.com/julie-tang00/point-bert"},{"title":"lulutang0608/Point-BERT","url":"https://github.com/lulutang0608/Point-BERT"},{"title":"lmd0311/pointmamba","url":"https://github.com/lmd0311/pointmamba"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":105951,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"MVTN","metrics":{"OBJ-BG (OA)":"92.6","OBJ-ONLY (OA)":"92.3","Overall Accuracy":"82.8"},"paper_url":"https://arxiv.org/abs/2011.13244v3","paper_title":"MVTN: Multi-View Transformation Network for 3D Shape Recognition","paper_date":"2020-11-26","code_links":[{"title":"ajhamdi/MVTN","url":"https://github.com/ajhamdi/MVTN"},{"title":"ajhamdi/mvtorch","url":"https://github.com/ajhamdi/mvtorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105952,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PRA-Net","metrics":{"Mean Accuracy":"79.1","Overall Accuracy":"82.1"},"paper_url":"https://arxiv.org/abs/2112.04903v1","paper_title":"PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis","paper_date":"2021-12-09","code_links":[{"title":"xiwuchen/pra-net","url":"https://github.com/xiwuchen/pra-net"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105953,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"DynamicScale","metrics":{"Overall Accuracy":"82.0"},"paper_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9565556","paper_title":"Dynamic Local Geometry Capture in 3D PointCloud Classification","paper_date":"2021-10-19","code_links":[{"title":"VimsLab/DynamicScale","url":"https://github.com/VimsLab/DynamicScale"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105954,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PatchAugment","metrics":{"Mean Accuracy":"79.7","Overall Accuracy":"81.0"},"paper_url":"https://openaccess.thecvf.com/content/ICCV2021W/DLGC/html/Sheshappanavar_PatchAugment_Local_Neighborhood_Augmentation_in_Point_Cloud_Classification_ICCVW_2021_paper.html","paper_title":"PatchAugment: Local Neighborhood Augmentation in Point Cloud Classification","paper_date":"2021-10-19","code_links":[{"title":"VimsLab/PatchAugment","url":"https://github.com/VimsLab/PatchAugment"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105955,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"GBNet","metrics":{"Mean Accuracy":"77.8","Overall Accuracy":"80.5"},"paper_url":"https://arxiv.org/abs/1911.12885v5","paper_title":"Geometric Back-projection Network for Point Cloud Classification","paper_date":"2019-11-28","code_links":[{"title":"ShiQiu0419/GFNet","url":"https://github.com/ShiQiu0419/GFNet"},{"title":"ShiQiu0419/GBNet","url":"https://github.com/ShiQiu0419/GBNet"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105956,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"SimpleView","metrics":{"Overall Accuracy":"80.5"},"paper_url":"https://openreview.net/forum?id=XwATtbX3oCz","paper_title":"Revisiting Point Cloud Classification with a Simple and Effective Baseline","paper_date":"2021-01-01","code_links":[{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"IsaacCorley/simpleview-pytorch","url":"https://github.com/IsaacCorley/simpleview-pytorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105957,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"DRNet","metrics":{"Mean Accuracy":"78.0","Overall Accuracy":"80.3"},"paper_url":"https://arxiv.org/abs/2005.06734v2","paper_title":"Dense-Resolution Network for Point Cloud Classification and Segmentation","paper_date":"2020-05-14","code_links":[{"title":"ShiQiu0419/DRNet","url":"https://github.com/ShiQiu0419/DRNet"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105958,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointCNN","metrics":{"Mean Accuracy":"75.1","OBJ-BG (OA)":"86.1","OBJ-ONLY (OA)":"85.5","Overall Accuracy":"78.5"},"paper_url":"http://arxiv.org/abs/1801.07791v5","paper_title":"PointCNN: Convolution On $\\mathcal{X}$-Transformed Points","paper_date":"2018-01-23","code_links":[{"title":"pyg-team/pytorch_geometric","url":"https://github.com/pyg-team/pytorch_geometric"},{"title":"yangyanli/PointCNN","url":"https://github.com/yangyanli/PointCNN"},{"title":"luost26/diffusion-point-cloud","url":"https://github.com/luost26/diffusion-point-cloud"},{"title":"nicolas-chaulet/torch-points3d","url":"https://github.com/nicolas-chaulet/torch-points3d"},{"title":"hxdengBerkeley/PointCNN.Pytorch","url":"https://github.com/hxdengBerkeley/PointCNN.Pytorch"},{"title":"octree-nn/ocnn-pytorch","url":"https://github.com/octree-nn/ocnn-pytorch"},{"title":"agarret7/PointCNN","url":"https://github.com/agarret7/PointCNN"},{"title":"chinakook/PointCNN.MX","url":"https://github.com/chinakook/PointCNN.MX"},{"title":"lanlan96/3drm","url":"https://github.com/lanlan96/3drm"},{"title":"NMADALI97/PointCNN_Pytorch","url":"https://github.com/NMADALI97/PointCNN_Pytorch"},{"title":"LebronGG/PointCnn","url":"https://github.com/LebronGG/PointCnn"},{"title":"Lw510107/PointCNN","url":"https://github.com/Lw510107/PointCNN"},{"title":"c3210927/point_cnn","url":"https://github.com/c3210927/point_cnn"},{"title":"tch/pointcnn","url":"https://github.com/tch/pointcnn"},{"title":"dream-chaser/pointcnn_for_3DFER","url":"https://github.com/dream-chaser/pointcnn_for_3DFER"},{"title":"tschattschneider/pointcnn","url":"https://github.com/tschattschneider/pointcnn"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105959,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"DGCNN","metrics":{"Mean Accuracy":"73.6","OBJ-BG (OA)":"82.8","OBJ-ONLY (OA)":"86.2","Overall Accuracy":"78.1"},"paper_url":"https://arxiv.org/abs/1801.07829v2","paper_title":"Dynamic Graph CNN for Learning on Point Clouds","paper_date":"2018-01-24","code_links":[{"title":"WangYueFt/dgcnn","url":"https://github.com/WangYueFt/dgcnn"},{"title":"vinits5/learning3d","url":"https://github.com/vinits5/learning3d"},{"title":"AnTao97/dgcnn.pytorch","url":"https://github.com/AnTao97/dgcnn.pytorch"},{"title":"bupt-gamma/gammagl","url":"https://github.com/bupt-gamma/gammagl"},{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"hqucms/ParticleNet","url":"https://github.com/hqucms/ParticleNet"},{"title":"lingzhang1/ContrastNet","url":"https://github.com/lingzhang1/ContrastNet"},{"title":"cy-xu/spatially_aware_ai","url":"https://github.com/cy-xu/spatially_aware_ai"},{"title":"yossilevii100/refocusing","url":"https://github.com/yossilevii100/refocusing"},{"title":"yossilevii100/critical_points2","url":"https://github.com/yossilevii100/critical_points2"},{"title":"hansen7/NRS_3D","url":"https://github.com/hansen7/NRS_3D"},{"title":"brent-murray/tr3d_pointaugdgcnn","url":"https://github.com/brent-murray/tr3d_pointaugdgcnn"},{"title":"nnn911/MLSI","url":"https://github.com/nnn911/MLSI"},{"title":"lingzhang1/dgcnn_sampling","url":"https://github.com/lingzhang1/dgcnn_sampling"},{"title":"lingzhang1/dgcnn_v2","url":"https://github.com/lingzhang1/dgcnn_v2"},{"title":"xrndai/dgcnn_amino_acid_structure","url":"https://github.com/xrndai/dgcnn_amino_acid_structure"},{"title":"JingfeiHuang/DGCNN-Paddle","url":"https://github.com/JingfeiHuang/DGCNN-Paddle"},{"title":"af13s/dgcnn-amino","url":"https://github.com/af13s/dgcnn-amino"},{"title":"Squanch-U/DGCNN","url":"https://github.com/Squanch-U/DGCNN"},{"title":"AmitBracha/GIP_project","url":"https://github.com/AmitBracha/GIP_project"},{"title":"gai-shaoyan/mind3d","url":"https://gitee.com/gai-shaoyan/mind3d"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105960,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointNet++","metrics":{"Mean Accuracy":"75.4","OBJ-BG (OA)":"82.3","OBJ-ONLY (OA)":"84.3","Overall Accuracy":"77.9"},"paper_url":"http://arxiv.org/abs/1706.02413v1","paper_title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","paper_date":"2017-06-07","code_links":[{"title":"yanx27/Pointnet_Pointnet2_pytorch","url":"https://github.com/yanx27/Pointnet_Pointnet2_pytorch"},{"title":"charlesq34/pointnet2","url":"https://github.com/charlesq34/pointnet2"},{"title":"facebookresearch/votenet","url":"https://github.com/facebookresearch/votenet"},{"title":"erikwijmans/Pointnet2_PyTorch","url":"https://github.com/erikwijmans/Pointnet2_PyTorch"},{"title":"rusty1s/pytorch_cluster","url":"https://github.com/rusty1s/pytorch_cluster"},{"title":"sshaoshuai/Pointnet2.PyTorch","url":"https://github.com/sshaoshuai/Pointnet2.PyTorch"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/pointnet2"},{"title":"zaiweizhang/H3DNet","url":"https://github.com/zaiweizhang/H3DNet"},{"title":"hehefan/P4Transformer","url":"https://github.com/hehefan/P4Transformer"},{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"thu17cyz/3DIoUMatch","url":"https://github.com/thu17cyz/3DIoUMatch"},{"title":"hehefan/PointRNN","url":"https://github.com/hehefan/PointRNN"},{"title":"facebookresearch/imvotenet","url":"https://github.com/facebookresearch/imvotenet"},{"title":"referit3d/referit3d","url":"https://github.com/referit3d/referit3d"},{"title":"hehefan/Point-Spatio-Temporal-Convolution","url":"https://github.com/hehefan/Point-Spatio-Temporal-Convolution"},{"title":"dgriffiths3/pointnet2-tensorflow2","url":"https://github.com/dgriffiths3/pointnet2-tensorflow2"},{"title":"nickgkan/beauty_detr","url":"https://github.com/nickgkan/beauty_detr"},{"title":"nickgkan/butd_detr","url":"https://github.com/nickgkan/butd_detr"},{"title":"open-air-sun/pq-transformer","url":"https://github.com/open-air-sun/pq-transformer"},{"title":"hehefan/PointRNN-PyTorch","url":"https://github.com/hehefan/PointRNN-PyTorch"},{"title":"joyhsu0504/ns3d","url":"https://github.com/joyhsu0504/ns3d"},{"title":"curryyuan/x-trans2cap","url":"https://github.com/curryyuan/x-trans2cap"},{"title":"zyang-ur/SAT","url":"https://github.com/zyang-ur/SAT"},{"title":"iballester/SPiKE","url":"https://github.com/iballester/SPiKE"},{"title":"johnsonsign/mast-pre","url":"https://github.com/johnsonsign/mast-pre"},{"title":"AsahiLiu/PointDetectron","url":"https://github.com/AsahiLiu/PointDetectron"},{"title":"hehefan/PSTNet2","url":"https://github.com/hehefan/PSTNet2"},{"title":"JohnsonSign/PointCMP","url":"https://github.com/JohnsonSign/PointCMP"},{"title":"dfki-av/mikasa-3dvg","url":"https://github.com/dfki-av/mikasa-3dvg"},{"title":"Ghailen-Ben-Achour/PointNet2_Segmentation","url":"https://github.com/Ghailen-Ben-Achour/PointNet2_Segmentation"},{"title":"houseleo/pointnet","url":"https://github.com/houseleo/pointnet"},{"title":"tao-tao-tao-tao-tao/diffusion_suction","url":"https://github.com/tao-tao-tao-tao-tao/diffusion_suction"},{"title":"Lonepic/SPIB","url":"https://github.com/Lonepic/SPIB"},{"title":"asalarpour/Point_GN","url":"https://github.com/asalarpour/Point_GN"},{"title":"LinZhuoChen/pointnet2_multi_gpu","url":"https://github.com/LinZhuoChen/pointnet2_multi_gpu"},{"title":"shaygu62/Protein-Classification","url":"https://github.com/shaygu62/Protein-Classification"},{"title":"zhh6425/LocalContextPropagation","url":"https://github.com/zhh6425/LocalContextPropagation"},{"title":"ikh-innovation/roboweldar-votenet","url":"https://github.com/ikh-innovation/roboweldar-votenet"},{"title":"witignite/Frustum-PointNet","url":"https://github.com/witignite/Frustum-PointNet"},{"title":"airalcorn2/parking-lot-pointnetplusplus","url":"https://github.com/airalcorn2/parking-lot-pointnetplusplus"},{"title":"ftdlyc/pointnet_pytorch","url":"https://github.com/ftdlyc/pointnet_pytorch"},{"title":"tingxueronghua/dpke","url":"https://github.com/tingxueronghua/dpke"},{"title":"timothylimyl/PointNet-Pytorch","url":"https://github.com/timothylimyl/PointNet-Pytorch"},{"title":"zhh6425/MotionPointNet","url":"https://github.com/zhh6425/MotionPointNet"},{"title":"alililia/ms_extend","url":"https://github.com/alililia/ms_extend/tree/main/ascend_pointnet2"},{"title":"hoangcuongbk80/VoteGrasp","url":"https://github.com/hoangcuongbk80/VoteGrasp"},{"title":"2024-MindSpore-1/Code4","url":"https://github.com/2024-MindSpore-1/Code4/tree/main/PointNet2"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/PointNet2"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/PointNet"},{"title":"alililia/ms_extend","url":"https://github.com/alililia/ms_extend/tree/main/gpu_pointnet2"},{"title":"tonysy/pointnet2_tf","url":"https://github.com/tonysy/pointnet2_tf"},{"title":"Xiangxu-0103/Octant-CNN","url":"https://github.com/Xiangxu-0103/Octant-CNN"},{"title":"Lw510107/PointNet","url":"https://github.com/Lw510107/PointNet"},{"title":"xurui1217/pointnet2-master","url":"https://github.com/xurui1217/pointnet2-master"},{"title":"SY-Xuan/pointnet_plus_plus_paddlepaddle","url":"https://github.com/SY-Xuan/pointnet_plus_plus_paddlepaddle"},{"title":"LONG-9621/VoteNet","url":"https://github.com/LONG-9621/VoteNet"},{"title":"LONG-9621/PointNet-","url":"https://github.com/LONG-9621/PointNet-"},{"title":"Harut0726/votenet","url":"https://github.com/Harut0726/votenet"},{"title":"FlowWind1999/pointnet-2","url":"https://github.com/FlowWind1999/pointnet-2"},{"title":"llzlcl/pointcloud-segment","url":"https://github.com/llzlcl/pointcloud-segment"},{"title":"zenroad/modifypointnet","url":"https://github.com/zenroad/modifypointnet"},{"title":"caizeyu1992/pointnet2","url":"https://github.com/caizeyu1992/pointnet2"},{"title":"2023-MindSpore-1/ms-code-8","url":"https://github.com/2023-MindSpore-1/ms-code-8/tree/main/PointNet2"},{"title":"gai-shaoyan/mind3d","url":"https://gitee.com/gai-shaoyan/mind3d"},{"title":"2023-MindSpore-1/ms-code-223","url":"https://github.com/2023-MindSpore-1/ms-code-223/tree/main/PointNet"},{"title":"MindSpore-paper-code-3/code4","url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/frustum-pointnet"},{"title":"2023-MindSpore-1/ms-code-223","url":"https://github.com/2023-MindSpore-1/ms-code-223/tree/main/PointNet2"},{"title":"brbzjl/pointnet2","url":"https://github.com/brbzjl/pointnet2"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105961,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"SpiderCNN","metrics":{"Mean Accuracy":"69.8","Overall Accuracy":"73.7"},"paper_url":"http://arxiv.org/abs/1803.11527v3","paper_title":"SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters","paper_date":"2018-03-30","code_links":[{"title":"xyf513/SpiderCNN","url":"https://github.com/xyf513/SpiderCNN"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105962,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"PointNet","metrics":{"Mean Accuracy":"63.4","Overall Accuracy":"68.2"},"paper_url":"http://arxiv.org/abs/1612.00593v2","paper_title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","paper_date":"2016-12-02","code_links":[{"title":"charlesq34/pointnet","url":"https://github.com/charlesq34/pointnet"},{"title":"fxia22/pointnet.pytorch","url":"https://github.com/fxia22/pointnet.pytorch"},{"title":"WangYueFt/dgcnn","url":"https://github.com/WangYueFt/dgcnn"},{"title":"vinits5/learning3d","url":"https://github.com/vinits5/learning3d"},{"title":"DylanWusee/pointconv_pytorch","url":"https://github.com/DylanWusee/pointconv_pytorch"},{"title":"nikitakaraevv/pointnet","url":"https://github.com/nikitakaraevv/pointnet"},{"title":"maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification","url":"https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification"},{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"sarthakTUM/roofn3d","url":"https://github.com/sarthakTUM/roofn3d"},{"title":"jtpils/treegan","url":"https://github.com/jtpils/treegan"},{"title":"ajhamdi/AdvPC","url":"https://github.com/ajhamdi/AdvPC"},{"title":"soumik12345/point-cloud-segmentation","url":"https://github.com/soumik12345/point-cloud-segmentation"},{"title":"AI-Guru/pointcloud_experiments","url":"https://github.com/AI-Guru/pointcloud_experiments"},{"title":"ali-stanford/pointnetcfd","url":"https://github.com/ali-stanford/pointnetcfd"},{"title":"romaintha/pytorch_pointnet","url":"https://github.com/romaintha/pytorch_pointnet"},{"title":"saaries/PointNet","url":"https://github.com/saaries/PointNet"},{"title":"Fragjacker/Pointcloud-grad-CAM","url":"https://github.com/Fragjacker/Pointcloud-grad-CAM"},{"title":"ZhihaoZhu/PointNet-Implementation-Tensorflow","url":"https://github.com/ZhihaoZhu/PointNet-Implementation-Tensorflow"},{"title":"YanWei123/Pytorch-implementation-of-FoldingNet-encoder-and-decoder-with-graph-pooling-covariance-add-quanti","url":"https://github.com/YanWei123/Pytorch-implementation-of-FoldingNet-encoder-and-decoder-with-graph-pooling-covariance-add-quanti"},{"title":"Yuto0107/pointnet","url":"https://github.com/Yuto0107/pointnet"},{"title":"YanWei123/PointNet-encoder-and-FoldingNet-decoder-add-quantization-change-latent-code-size-from-512-to-1024","url":"https://github.com/YanWei123/PointNet-encoder-and-FoldingNet-decoder-add-quantization-change-latent-code-size-from-512-to-1024"},{"title":"opeco17/pointnet","url":"https://github.com/opeco17/pointnet"},{"title":"Dir-b/PointNet","url":"https://github.com/Dir-b/PointNet"},{"title":"Young98CN/pointconv_pytorch","url":"https://github.com/Young98CN/pointconv_pytorch"},{"title":"y2kmz/pointnetv2","url":"https://github.com/y2kmz/pointnetv2"},{"title":"YanWei123/Pointnet_encoder_Foldingnet_decoder_quantization","url":"https://github.com/YanWei123/Pointnet_encoder_Foldingnet_decoder_quantization"},{"title":"imanlab/deep_movement_primitives","url":"https://github.com/imanlab/deep_movement_primitives"},{"title":"abdullahozer11/Segmentation-and-Classification-of-Objects-in-Point-Clouds","url":"https://github.com/abdullahozer11/Segmentation-and-Classification-of-Objects-in-Point-Clouds"},{"title":"donshen/pointnet.phasedetection","url":"https://github.com/donshen/pointnet.phasedetection"},{"title":"ModelBunker/PointNet-TensorFlow","url":"https://github.com/ModelBunker/PointNet-TensorFlow"},{"title":"amyllykoski/CycleGAN","url":"https://github.com/amyllykoski/CycleGAN"},{"title":"Javed002/Object_detection_PointNet","url":"https://github.com/Javed002/Object_detection_PointNet"},{"title":"sanantoniochili/PointCloud_KNN","url":"https://github.com/sanantoniochili/PointCloud_KNN"},{"title":"PaParaZz1/PointNet","url":"https://github.com/PaParaZz1/PointNet"},{"title":"yevgm/deepadv3d","url":"https://github.com/yevgm/deepadv3d"},{"title":"witignite/Frustum-PointNet","url":"https://github.com/witignite/Frustum-PointNet"},{"title":"m-117/PointNet-ein-Implementationsbeispiel-mit-Jupyter-Notebooks","url":"https://github.com/m-117/PointNet-ein-Implementationsbeispiel-mit-Jupyter-Notebooks"},{"title":"alpemek/ais3d","url":"https://github.com/alpemek/ais3d"},{"title":"yanxp/PointNet","url":"https://github.com/yanxp/PointNet"},{"title":"ftdlyc/pointnet_pytorch","url":"https://github.com/ftdlyc/pointnet_pytorch"},{"title":"Melo-Wang/Deep-Learning-on-Point-Cloud-of-Aerospace-Components-for-3D-Classification","url":"https://github.com/Melo-Wang/Deep-Learning-on-Point-Cloud-of-Aerospace-Components-for-3D-Classification"},{"title":"Phimos/Paddle-PointNet","url":"https://github.com/Phimos/Paddle-PointNet"},{"title":"zgx0534/pointnet_win","url":"https://github.com/zgx0534/pointnet_win"},{"title":"timothylimyl/PointNet-Pytorch","url":"https://github.com/timothylimyl/PointNet-Pytorch"},{"title":"minhncedutw/pointnet1_keras","url":"https://github.com/minhncedutw/pointnet1_keras"},{"title":"Jagyan/ghost_radarpoint_detection","url":"https://github.com/Jagyan/ghost_radarpoint_detection"},{"title":"brendanmallery9/entropic-barycenters","url":"https://github.com/brendanmallery9/entropic-barycenters"},{"title":"2024-MindSpore-1/Code4","url":"https://github.com/2024-MindSpore-1/Code4/tree/main/PointNet"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/frustum-pointnet"},{"title":"xiuyu0000/vision","url":"https://github.com/xiuyu0000/vision/blob/main/mindvision/ms3d/models/pointnet2cls.py"},{"title":"hnmspirit/pointnet1","url":"https://github.com/hnmspirit/pointnet1"},{"title":"yangyucheng000/pointnet","url":"https://github.com/yangyucheng000/pointnet"},{"title":"eth212/Qmind_ModelNet10_PointNet","url":"https://github.com/eth212/Qmind_ModelNet10_PointNet"},{"title":"smfirmin/DeepLearningFinalProject","url":"https://github.com/smfirmin/DeepLearningFinalProject"},{"title":"ECE685-FinalProject/3D-object-recognition","url":"https://github.com/ECE685-FinalProject/3D-object-recognition"},{"title":"KhusDM/PointNetTree","url":"https://github.com/KhusDM/PointNetTree"},{"title":"Lw510107/pointnet-2018.6.27-","url":"https://github.com/Lw510107/pointnet-2018.6.27-"},{"title":"xurui1217/pointnet.pytorch-master","url":"https://github.com/xurui1217/pointnet.pytorch-master"},{"title":"hnVfly/pointnet.mxnet","url":"https://github.com/hnVfly/pointnet.mxnet"},{"title":"LebronGG/PointNet","url":"https://github.com/LebronGG/PointNet"},{"title":"GOD-GOD-Autonomous-Vehicle/self-pointnet","url":"https://github.com/GOD-GOD-Autonomous-Vehicle/self-pointnet"},{"title":"AlfredoZermini/PointNet","url":"https://github.com/AlfredoZermini/PointNet"},{"title":"wonderland-dsg/pointnet-grid","url":"https://github.com/wonderland-dsg/pointnet-grid"},{"title":"aviros/roatationPointnet","url":"https://github.com/aviros/roatationPointnet"},{"title":"THHHomas/mls","url":"https://github.com/THHHomas/mls"},{"title":"liuch37/pointnet","url":"https://github.com/liuch37/pointnet"},{"title":"yanx27/Pointnet","url":"https://github.com/yanx27/Pointnet"},{"title":"Taeuk-Jang/pointcompletion","url":"https://github.com/Taeuk-Jang/pointcompletion"},{"title":"ytng001/sensemaking","url":"https://github.com/ytng001/sensemaking"},{"title":"nddoshi/pointnet","url":"https://github.com/nddoshi/pointnet"},{"title":"SY-Xuan/pointnet_paddle","url":"https://github.com/SY-Xuan/pointnet_paddle"},{"title":"Cmeijiang/PointNet_MS","url":"https://github.com/Cmeijiang/PointNet_MS"},{"title":"AndreiMoraru123/PointNet","url":"https://github.com/AndreiMoraru123/PointNet"},{"title":"mengxingshifen1218/pointnet.pytorch","url":"https://github.com/mengxingshifen1218/pointnet.pytorch"},{"title":"Moon-Xuezha/PointNet","url":"https://github.com/Moon-Xuezha/PointNet"},{"title":"ajertec/PointNetKeras","url":"https://github.com/ajertec/PointNetKeras"},{"title":"2023-MindSpore-1/ms-code-35","url":"https://github.com/2023-MindSpore-1/ms-code-35"},{"title":"LONG-9621/Extract_Point_3D","url":"https://github.com/LONG-9621/Extract_Point_3D"},{"title":"Mind23-2/MindCode-63","url":"https://github.com/Mind23-2/MindCode-63"},{"title":"merazlab/3D_Deep_Learning_Link","url":"https://github.com/merazlab/3D_Deep_Learning_Link"},{"title":"2023-MindSpore-1/ms-code-7","url":"https://github.com/2023-MindSpore-1/ms-code-7/tree/main/PointNet"},{"title":"KaidongLi/tf-3d-alpha","url":"https://github.com/KaidongLi/tf-3d-alpha"},{"title":"gai-shaoyan/mind3d","url":"https://gitee.com/gai-shaoyan/mind3d"},{"title":"prasadsawant5/PointNet","url":"https://github.com/prasadsawant5/PointNet"},{"title":"SonuDileep/3-D-Object-Detection-using-PointNet","url":"https://github.com/SonuDileep/3-D-Object-Detection-using-PointNet"},{"title":"BPMJG/annotated_pointnet","url":"https://github.com/BPMJG/annotated_pointnet"},{"title":"debajyotid2/pointnet_pl","url":"https://github.com/debajyotid2/pointnet_pl"},{"title":"SBPL-Cruz/perch_pose_sampler","url":"https://github.com/SBPL-Cruz/perch_pose_sampler"},{"title":"2023-MindSpore-4/Code9","url":"https://github.com/2023-MindSpore-4/Code9/tree/main/PointNet"},{"title":"wuryantoAji/POINTNET","url":"https://github.com/wuryantoAji/POINTNET"},{"title":"LONG-9621/PointNet","url":"https://github.com/LONG-9621/PointNet"},{"title":"bt77/pointnet","url":"https://github.com/bt77/pointnet"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/PointNet2"},{"title":"KiranAkadas/My_Pointnet_v2","url":"https://github.com/KiranAkadas/My_Pointnet_v2"},{"title":"YiruS/pointnet_adversarial","url":"https://github.com/YiruS/pointnet_adversarial"},{"title":"Harut0726/my-pointnet-tensorflow","url":"https://github.com/Harut0726/my-pointnet-tensorflow"},{"title":"AlvesRobot/Deep-Learning-on-Point-Cloud-for-3D-Classification-and-Segmentation","url":"https://github.com/AlvesRobot/Deep-Learning-on-Point-Cloud-for-3D-Classification-and-Segmentation"},{"title":"hz-ants/pointnet.pytorch","url":"https://github.com/hz-ants/pointnet.pytorch"},{"title":"VaanHUANG/CSCI5210HW1","url":"https://github.com/VaanHUANG/CSCI5210HW1"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/PointNet"},{"title":"ShadowShadowWong/update-pointnet-work","url":"https://github.com/ShadowShadowWong/update-pointnet-work"},{"title":"Yang2446/pointnet","url":"https://github.com/Yang2446/pointnet"},{"title":"lingzhang1/pointnet_pytorch","url":"https://github.com/lingzhang1/pointnet_pytorch"},{"title":"dwtstore/sfm1","url":"https://github.com/dwtstore/sfm1"},{"title":"freddieee/pn_6d_single","url":"https://github.com/freddieee/pn_6d_single"},{"title":"ahmed-anas/thesis-pointnet","url":"https://github.com/ahmed-anas/thesis-pointnet"},{"title":"coconutzs/PointNet_zs","url":"https://github.com/coconutzs/PointNet_zs"},{"title":"CheesyB/cpointnet","url":"https://github.com/CheesyB/cpointnet"},{"title":"lingzhang1/pointnet_tensorflow","url":"https://github.com/lingzhang1/pointnet_tensorflow"},{"title":"aviros/pointnet_totations","url":"https://github.com/aviros/pointnet_totations"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":105963,"task":"3D Point Cloud Classification","parent_task":null,"dataset":"ScanObjectNN","model_name":"ExpPoint-MAE","metrics":{"OBJ-BG (OA)":"90.88","OBJ-ONLY (OA)":"90.02"},"paper_url":"https://arxiv.org/abs/2306.10798v3","paper_title":"ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformers","paper_date":"2023-06-19","code_links":[{"title":"vvrpanda/exppoint-mae","url":"https://github.com/vvrpanda/exppoint-mae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":145985,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"OmniVec2","metrics":{"Overall Accuracy":"97.2"},"paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Srivastava_OmniVec2_-_A_Novel_Transformer_based_Network_for_Large_Scale_CVPR_2024_paper.html","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","paper_date":"2024-01-01","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":145986,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointGST","metrics":{"OBJ-BG (OA)":"99.48","OBJ-ONLY (OA)":"97.76","Overall Accuracy":"96.18"},"paper_url":"https://arxiv.org/abs/2410.08114v1","paper_title":"Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning","paper_date":"2024-10-10","code_links":[{"title":"jerryfeng2003/pointgst","url":"https://github.com/jerryfeng2003/pointgst"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":145987,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"OmniVec","metrics":{"Overall Accuracy":"96.1"},"paper_url":"https://arxiv.org/abs/2311.05709v1","paper_title":"OmniVec: Learning robust representations with cross modal sharing","paper_date":"2023-11-07","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":145988,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"GPSFormer","metrics":{"FLOPs":"0.7G","Mean Accuracy":"93.8","Number of params":"2.36M","Overall Accuracy":"95.4"},"paper_url":"https://arxiv.org/abs/2407.13519v2","paper_title":"GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding","paper_date":"2024-07-18","code_links":[{"title":"changshuowang/GPSFormer","url":"https://github.com/changshuowang/GPSFormer"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":145989,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ReCon++","metrics":{"OBJ-BG (OA)":"98.80","OBJ-ONLY (OA)":"97.59","Overall Accuracy":"95.25"},"paper_url":"https://arxiv.org/abs/2402.17766v3","paper_title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","paper_date":"2024-02-27","code_links":[{"title":"qizekun/ShapeLLM","url":"https://github.com/qizekun/ShapeLLM"},{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":145990,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"AsymDSD-B* (no voting)","metrics":{"OBJ-BG (OA)":"96.73","OBJ-ONLY (OA)":"94.32","Overall Accuracy":"93.72"},"paper_url":"https://arxiv.org/abs/2506.21724v1","paper_title":"Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning","paper_date":"2025-06-26","code_links":[{"title":"RFLeijenaar/AsymDSD","url":"https://github.com/RFLeijenaar/AsymDSD"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":145991,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointGPT","metrics":{"OBJ-BG (OA)":"97.2","OBJ-ONLY (OA)":"96.6","Overall Accuracy":"93.4"},"paper_url":"https://arxiv.org/abs/2305.11487v2","paper_title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","paper_date":"2023-05-19","code_links":[{"title":"CGuangyan-BIT/PointGPT","url":"https://github.com/CGuangyan-BIT/PointGPT"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":145992,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"GPSFormer-elite","metrics":{"Mean Accuracy":"92.51","Number of params":"0.68M","Overall Accuracy":"93.30"},"paper_url":"https://arxiv.org/abs/2407.13519v2","paper_title":"GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding","paper_date":"2024-07-18","code_links":[{"title":"changshuowang/GPSFormer","url":"https://github.com/changshuowang/GPSFormer"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":145993,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Mamba3D","metrics":{"FLOPs":"3.9G","Number of params":"16.9M","OBJ-BG (OA)":"94.49","OBJ-ONLY (OA)":"92.43","Overall Accuracy":"92.64"},"paper_url":"https://arxiv.org/abs/2404.14966v2","paper_title":"Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model","paper_date":"2024-04-23","code_links":[{"title":"xhanxu/Mamba3D","url":"https://github.com/xhanxu/Mamba3D"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":145994,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Mamba3D (no voting)","metrics":{"FLOPs":"3.9G","Number of params":"16.9M","OBJ-BG (OA)":"92.94","OBJ-ONLY (OA)":"92.08","Overall Accuracy":"91.81"},"paper_url":"https://arxiv.org/abs/2404.14966v2","paper_title":"Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model","paper_date":"2024-04-23","code_links":[{"title":"xhanxu/Mamba3D","url":"https://github.com/xhanxu/Mamba3D"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":145995,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP-2 + PointNeXt","metrics":{"Mean Accuracy":"91.2","Number of params":"1.4M","Overall Accuracy":"91.5"},"paper_url":"https://arxiv.org/abs/2305.08275v4","paper_title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","paper_date":"2023-05-14","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":145996,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ReCon","metrics":{"OBJ-BG (OA)":"95.35","OBJ-ONLY (OA)":"93.80","Overall Accuracy":"91.26"},"paper_url":"https://arxiv.org/abs/2302.02318v2","paper_title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","paper_date":"2023-02-05","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"aHapBean/PCP-MAE","url":"https://github.com/aHapBean/PCP-MAE"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":145997,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP-2 + PointNeXt (no voting)","metrics":{"Mean Accuracy":"90.3","Number of params":"1.4M","Overall Accuracy":"90.8"},"paper_url":"https://arxiv.org/abs/2305.08275v4","paper_title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","paper_date":"2023-05-14","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":145998,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ReCon (no voting)","metrics":{"OBJ-BG (OA)":"95.18","OBJ-ONLY (OA)":"93.29","Overall Accuracy":"90.63"},"paper_url":"https://arxiv.org/abs/2302.02318v2","paper_title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","paper_date":"2023-02-05","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"aHapBean/PCP-MAE","url":"https://github.com/aHapBean/PCP-MAE"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":145999,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"AsymDSD-S (no voting)","metrics":{"OBJ-BG (OA)":"94.32","OBJ-ONLY (OA)":"91.91","Overall Accuracy":"90.53"},"paper_url":"https://arxiv.org/abs/2506.21724v1","paper_title":"Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning","paper_date":"2025-06-26","code_links":[{"title":"RFLeijenaar/AsymDSD","url":"https://github.com/RFLeijenaar/AsymDSD"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146000,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DeLA","metrics":{"FLOPs":"1.5G","Mean Accuracy":"89.3","Number of params":"5.3M","Overall Accuracy":"90.4"},"paper_url":"https://arxiv.org/abs/2308.16532v1","paper_title":"Decoupled Local Aggregation for Point Cloud Learning","paper_date":"2023-08-31","code_links":[{"title":"matrix-asc/dela","url":"https://github.com/matrix-asc/dela"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146001,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PCP-MAE","metrics":{"OBJ-BG (OA)":"95.52","OBJ-ONLY (OA)":"94.32","Overall Accuracy":"90.35"},"paper_url":"https://arxiv.org/abs/2408.08753v2","paper_title":"PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders","paper_date":"2024-08-16","code_links":[{"title":"aHapBean/PCP-MAE","url":"https://github.com/aHapBean/PCP-MAE"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146002,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointConT","metrics":{"Mean Accuracy":"88.5","Overall Accuracy":"90.3"},"paper_url":"https://arxiv.org/abs/2303.04599v1","paper_title":"Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space","paper_date":"2023-03-08","code_links":[{"title":"yahuiliu99/pointcont","url":"https://github.com/yahuiliu99/pointcont"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146003,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-RAE (no voting)","metrics":{"OBJ-BG (OA)":"95.53","OBJ-ONLY (OA)":"93.63","Overall Accuracy":"90.28"},"paper_url":"https://arxiv.org/abs/2310.03670v1","paper_title":"Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning","paper_date":"2023-09-25","code_links":[{"title":"liuyyy111/point-rae","url":"https://github.com/liuyyy111/point-rae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146004,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-FEMAE","metrics":{"OBJ-BG (OA)":"95.18","OBJ-ONLY (OA)":"93.29","Overall Accuracy":"90.22"},"paper_url":"https://arxiv.org/abs/2312.10726v1","paper_title":"Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders","paper_date":"2023-12-17","code_links":[{"title":"zyh16143998882/aaai24-pointfemae","url":"https://github.com/zyh16143998882/aaai24-pointfemae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146005,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"I2P-MAE (no voting)","metrics":{"OBJ-BG (OA)":"94.15","OBJ-ONLY (OA)":"91.57","Overall Accuracy":"90.11"},"paper_url":"https://arxiv.org/abs/2212.06785v1","paper_title":"Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders","paper_date":"2022-12-13","code_links":[{"title":"zrrskywalker/i2p-mae","url":"https://github.com/zrrskywalker/i2p-mae"},{"title":"zrrskywalker/point-m2ae","url":"https://github.com/zrrskywalker/point-m2ae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146006,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP + PointNeXt","metrics":{"Mean Accuracy":"88.6","Number of params":"1.4M","Overall Accuracy":"89.7"},"paper_url":"https://arxiv.org/abs/2212.05171v4","paper_title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","paper_date":"2022-12-10","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146007,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ReCon+PPT","metrics":{"OBJ-BG (OA)":"95.01","OBJ-ONLY (OA)":"93.28","Overall Accuracy":"89.52"},"paper_url":"https://arxiv.org/abs/2408.11567v1","paper_title":"Positional Prompt Tuning for Efficient 3D Representation Learning","paper_date":"2024-08-21","code_links":[{"title":"zsc000722/ppt","url":"https://github.com/zsc000722/ppt"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146008,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"3D-JEPA","metrics":{"OBJ-BG (OA)":"93.63","OBJ-ONLY (OA)":"94.49","Overall Accuracy":"89.52"},"paper_url":"https://arxiv.org/abs/2409.15803v1","paper_title":"3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning","paper_date":"2024-09-24","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146009,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointMLP∗ + JM3D","metrics":{"Mean Accuracy":"88.7","Overall Accuracy":"89.5"},"paper_url":"https://arxiv.org/abs/2308.02982v2","paper_title":"Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation","paper_date":"2023-08-06","code_links":[{"title":"mr-neko/jm3d","url":"https://github.com/mr-neko/jm3d"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146010,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP + PointMLP","metrics":{"Mean Accuracy":"88.5","Overall Accuracy":"89.4"},"paper_url":"https://arxiv.org/abs/2212.05171v4","paper_title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","paper_date":"2022-12-10","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146011,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"KPConvX-L","metrics":{"Mean Accuracy":"88.1","Overall Accuracy":"89.3"},"paper_url":"https://arxiv.org/abs/2405.13194v1","paper_title":"KPConvX: Modernizing Kernel Point Convolution with Kernel Attention","paper_date":"2024-05-21","code_links":[{"title":"apple/ml-kpconvx","url":"https://github.com/apple/ml-kpconvx"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146012,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"P2P","metrics":{"Number of params":"195.8M","Overall Accuracy":"89.3"},"paper_url":"https://arxiv.org/abs/2208.02812v2","paper_title":"P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting","paper_date":"2022-08-04","code_links":[{"title":"wangzy22/P2P","url":"https://github.com/wangzy22/P2P"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146013,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ACT","metrics":{"Overall Accuracy":"89.17"},"paper_url":"https://arxiv.org/abs/2212.08320v2","paper_title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","paper_date":"2022-12-16","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146014,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Ours","metrics":{"Mean Accuracy":"87.2","Overall Accuracy":"89.0"},"paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320324004631","paper_title":"Beyond local patches: Preserving global–local interactions by enhancing self-attention via 3D point cloud tokenization","paper_date":"2024-11-01","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146015,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"OTMae3D","metrics":{"FLOPs":"6.29","OBJ-BG (OA)":"92.9","OBJ-ONLY (OA)":"92.3","Overall Accuracy":"89.0"},"paper_url":"https://ieeexplore.ieee.org/document/10815033","paper_title":"Rethinking Masked Representation Learning for 3D Point Cloud Understanding","paper_date":"2024-12-26","code_links":[{"title":"OpenSpaceAI/OTMae3D","url":"https://github.com/OpenSpaceAI/OTMae3D"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146016,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP-2 + Point-BERT","metrics":{"Overall Accuracy":"89.0"},"paper_url":"https://arxiv.org/abs/2305.08275v4","paper_title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","paper_date":"2023-05-14","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146017,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNeXt+Local","metrics":{"Mean Accuracy":"87.4","Overall Accuracy":"88.6"},"paper_url":"https://arxiv.org/abs/2212.05140v2","paper_title":"Local Neighborhood Features for 3D Classification","paper_date":"2022-12-09","code_links":[{"title":"VimsLab/Local3DFeatures","url":"https://github.com/VimsLab/Local3DFeatures"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146018,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"SPoTr","metrics":{"Mean Accuracy":"86.8","Overall Accuracy":"88.6"},"paper_url":"https://arxiv.org/abs/2303.16450v1","paper_title":"Self-positioning Point-based Transformer for Point Cloud Understanding","paper_date":"2023-03-29","code_links":[{"title":"mlvlab/spotr","url":"https://github.com/mlvlab/spotr"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146019,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"IDPT","metrics":{"OBJ-BG (OA)":"93.12","Overall Accuracy":"88.51"},"paper_url":"https://arxiv.org/abs/2304.07221v2","paper_title":"Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models","paper_date":"2023-04-14","code_links":[{"title":"zyh16143998882/iccv23-idpt","url":"https://github.com/zyh16143998882/iccv23-idpt"},{"title":"zyh16143998882/IDPT","url":"https://github.com/zyh16143998882/IDPT"},{"title":"zyh16143998882/aaai24-pointfemae","url":"https://github.com/zyh16143998882/aaai24-pointfemae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146020,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointMLP+TAP","metrics":{"Overall Accuracy":"88.5"},"paper_url":"https://arxiv.org/abs/2307.14971v2","paper_title":"Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models","paper_date":"2023-07-27","code_links":[{"title":"wangzy22/tap","url":"https://github.com/wangzy22/tap"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146021,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNeXt+GAM","metrics":{"FLOPs":"1.64G","Number of params":"1.4M","Overall Accuracy":"88.4"},"paper_url":"http://arxiv.org/abs/1505.07110v2","paper_title":"$(0, 4)$ dualities","paper_date":"2015-12-14","code_links":[],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146022,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNeXt+HyCoRe","metrics":{"Mean Accuracy":"87.0","Overall Accuracy":"88.3"},"paper_url":"https://arxiv.org/abs/2209.10318v1","paper_title":"Rethinking the compositionality of point clouds through regularization in the hyperbolic space","paper_date":"2022-09-21","code_links":[{"title":"diegovalsesia/hycore","url":"https://github.com/diegovalsesia/hycore"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146023,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ACT (no voting)","metrics":{"OBJ-BG (OA)":"93.29","OBJ-ONLY (OA)":"91.91","Overall Accuracy":"88.21"},"paper_url":"https://arxiv.org/abs/2212.08320v2","paper_title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","paper_date":"2022-12-16","code_links":[{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"},{"title":"asterisci/point-gcc","url":"https://github.com/asterisci/point-gcc"},{"title":"qizekun/vpp","url":"https://github.com/qizekun/vpp"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146024,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNeXt","metrics":{"FLOPs":"1.64G","Mean Accuracy":"86.8","Number of params":"1.4M","Overall Accuracy":"88.2"},"paper_url":"https://arxiv.org/abs/2206.04670v2","paper_title":"PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies","paper_date":"2022-06-09","code_links":[{"title":"guochengqian/pointnext","url":"https://github.com/guochengqian/pointnext"},{"title":"linhaojia13/pointmetabase","url":"https://github.com/linhaojia13/pointmetabase"},{"title":"boyden/pointtransformerfl","url":"https://github.com/boyden/pointtransformerfl"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146025,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointConT (no voting)","metrics":{"Mean Accuracy":"86.0","Overall Accuracy":"88.0"},"paper_url":"https://arxiv.org/abs/2303.04599v1","paper_title":"Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space","paper_date":"2023-03-08","code_links":[{"title":"yahuiliu99/pointcont","url":"https://github.com/yahuiliu99/pointcont"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146026,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointVector-S","metrics":{"Mean Accuracy":"86.2","Overall Accuracy":"87.8"},"paper_url":"https://arxiv.org/abs/2205.10528v3","paper_title":"PointVector: A Vector Representation In Point Cloud Analysis","paper_date":"2022-05-21","code_links":[{"title":"guochengqian/openpoints","url":"https://github.com/guochengqian/openpoints/blob/master/models/backbone/pointvector.py"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146027,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"point2vec","metrics":{"Mean Accuracy":"86.0","OBJ-BG (OA)":"91.2","OBJ-ONLY (OA)":"90.4","Overall Accuracy":"87.5"},"paper_url":"https://arxiv.org/abs/2303.16570v2","paper_title":"Point2Vec for Self-Supervised Representation Learning on Point Clouds","paper_date":"2023-03-29","code_links":[{"title":"kabouzeid/point2vec","url":"https://github.com/kabouzeid/point2vec"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146028,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointStack","metrics":{"Mean Accuracy":"86.2","Overall Accuracy":"87.2"},"paper_url":"https://arxiv.org/abs/2205.09962v1","paper_title":"Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling","paper_date":"2022-05-20","code_links":[{"title":"LongerVision/PointStack","url":"https://github.com/LongerVision/PointStack"},{"title":"kaist-avelab/PointStack","url":"https://github.com/kaist-avelab/PointStack"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146029,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-PN","metrics":{"Number of params":"0.8M","Overall Accuracy":"87.1"},"paper_url":"https://arxiv.org/abs/2303.08134v2","paper_title":"Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis","paper_date":"2023-03-14","code_links":[{"title":"zrrskywalker/point-nn","url":"https://github.com/zrrskywalker/point-nn"},{"title":"opengvlab/cafo","url":"https://github.com/opengvlab/cafo"},{"title":"asalarpour/Point_GN","url":"https://github.com/asalarpour/Point_GN"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146030,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointCMT","metrics":{"Mean Accuracy":"84.8","Number of params":"12.6M","Overall Accuracy":"86.7"},"paper_url":"https://arxiv.org/abs/2210.04208v1","paper_title":"Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis","paper_date":"2022-10-09","code_links":[{"title":"yanx27/2dpass","url":"https://github.com/yanx27/2dpass"},{"title":"zhanheshen/pointcmt","url":"https://github.com/zhanheshen/pointcmt"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146031,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-JEPA","metrics":{"OBJ-BG (OA)":"92.9±0.4","Overall Accuracy":"86.6"},"paper_url":"https://arxiv.org/abs/2404.16432v5","paper_title":"Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud","paper_date":"2024-04-25","code_links":[{"title":"Ayumu-J-S/Point-JEPA","url":"https://github.com/Ayumu-J-S/Point-JEPA"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146032,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointMLS","metrics":{"Overall Accuracy":"86.6"},"paper_url":"https://arxiv.org/abs/2401.08210v1","paper_title":"ModelNet-O: A Large-Scale Synthetic Dataset for Occlusion-Aware Point Cloud Classification","paper_date":"2024-01-16","code_links":[{"title":"fanglaosi/pointmls","url":"https://github.com/fanglaosi/pointmls"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146033,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-M2AE","metrics":{"OBJ-BG (OA)":"91.22","OBJ-ONLY (OA)":"88.81","Overall Accuracy":"86.43"},"paper_url":"https://arxiv.org/abs/2205.14401v2","paper_title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","paper_date":"2022-05-28","code_links":[{"title":"zrrskywalker/i2p-mae","url":"https://github.com/zrrskywalker/i2p-mae"},{"title":"zrrskywalker/point-m2ae","url":"https://github.com/zrrskywalker/point-m2ae"},{"title":"MindSpore-paper-code-2/code400","url":"https://github.com/MindSpore-paper-code-2/code400/tree/main/MAE"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146034,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ULIP + PointBERT","metrics":{"Overall Accuracy":"86.4"},"paper_url":"https://arxiv.org/abs/2212.05171v4","paper_title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","paper_date":"2022-12-10","code_links":[{"title":"salesforce/ulip","url":"https://github.com/salesforce/ulip"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146035,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DualMLP","metrics":{"Overall Accuracy":"86.4"},"paper_url":"https://link.springer.com/article/10.1007/s00371-023-03114-3","paper_title":"DualMLP: a two-stream fusion model for 3D point cloud classification","paper_date":"2023-10-10","code_links":[{"title":"snehaputul/DualMLP","url":"https://github.com/snehaputul/DualMLP"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146036,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"RepSurf-U (2x)","metrics":{"FLOPs":"2.43G","Number of params":"6.80M","Overall Accuracy":"86.0"},"paper_url":"https://arxiv.org/abs/2205.05740v2","paper_title":"Surface Representation for Point Clouds","paper_date":"2022-05-11","code_links":[{"title":"hancyran/RepSurf","url":"https://github.com/hancyran/RepSurf"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146037,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointMLP","metrics":{"Mean Accuracy":"84.4","Overall Accuracy":"85.7"},"paper_url":"https://arxiv.org/abs/2202.07123v2","paper_title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","paper_date":"2022-02-15","code_links":[{"title":"ma-xu/pointmlp-pytorch","url":"https://github.com/ma-xu/pointmlp-pytorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146038,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-LGMask","metrics":{"OBJ-BG (OA)":"89.8","OBJ-ONLY (OA)":"89.3","Overall Accuracy":"85.3"},"paper_url":"https://ieeexplore.ieee.org/abstract/document/10146493","paper_title":"Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking","paper_date":"2023-06-08","code_links":[{"title":"TangYuan96/Point-LGMask","url":"https://github.com/TangYuan96/Point-LGMask"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146039,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-MAE","metrics":{"OBJ-BG (OA)":"90.02","OBJ-ONLY (OA)":"88.29","Overall Accuracy":"85.2"},"paper_url":"https://arxiv.org/abs/2203.06604v2","paper_title":"Masked Autoencoders for Point Cloud Self-supervised Learning","paper_date":"2022-03-13","code_links":[{"title":"Pang-Yatian/Point-MAE","url":"https://github.com/Pang-Yatian/Point-MAE"},{"title":"lmd0311/pointmamba","url":"https://github.com/lmd0311/pointmamba"},{"title":"vvrpanda/exppoint-mae","url":"https://github.com/vvrpanda/exppoint-mae"},{"title":"liujia99/tpm","url":"https://github.com/liujia99/tpm"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146040,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"MVTN+SimpleView++","metrics":{"Overall Accuracy":"84.8"},"paper_url":"https://ieeexplore.ieee.org/document/9874679","paper_title":"SimpleView++: Neighborhood Views for Point Cloud Classification","paper_date":"2022-09-08","code_links":[{"title":"VimsLab/SimpleViewPlusPlus","url":"https://github.com/VimsLab/SimpleViewPlusPlus"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146041,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DeltaConv","metrics":{"Overall Accuracy":"84.7"},"paper_url":"https://arxiv.org/abs/2111.08799v5","paper_title":"DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds","paper_date":"2021-11-16","code_links":[{"title":"rubenwiersma/deltaconv","url":"https://github.com/rubenwiersma/deltaconv"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146042,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"RepSurf-U","metrics":{"FLOPs":"0.81G","Number of params":"1.48M","Overall Accuracy":"84.6"},"paper_url":"https://arxiv.org/abs/2205.05740v2","paper_title":"Surface Representation for Point Clouds","paper_date":"2022-05-11","code_links":[{"title":"hancyran/RepSurf","url":"https://github.com/hancyran/RepSurf"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146043,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"APP-Net","metrics":{"Overall Accuracy":"84.1"},"paper_url":"https://arxiv.org/abs/2205.00847v2","paper_title":"APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification","paper_date":"2022-05-02","code_links":[{"title":"mcg-nju/app-net","url":"https://github.com/mcg-nju/app-net"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146044,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointMLP-elite","metrics":{"Mean Accuracy":"81.8","Overall Accuracy":" 83.8"},"paper_url":"https://arxiv.org/abs/2202.07123v2","paper_title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","paper_date":"2022-02-15","code_links":[{"title":"ma-xu/pointmlp-pytorch","url":"https://github.com/ma-xu/pointmlp-pytorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146045,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNet++ + SageMix","metrics":{"Overall Accuracy":"83.7"},"paper_url":"https://arxiv.org/abs/2210.06944v1","paper_title":"SageMix: Saliency-Guided Mixup for Point Clouds","paper_date":"2022-10-13","code_links":[{"title":"mlvlab/SageMix","url":"https://github.com/mlvlab/SageMix"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146046,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DGCNN + SageMix","metrics":{"Overall Accuracy":"83.6"},"paper_url":"https://arxiv.org/abs/2210.06944v1","paper_title":"SageMix: Saliency-Guided Mixup for Point Clouds","paper_date":"2022-10-13","code_links":[{"title":"mlvlab/SageMix","url":"https://github.com/mlvlab/SageMix"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146047,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-TnT","metrics":{"FLOPs":"1.19G","Mean Accuracy":"81.0","Number of params":"3.9M","Overall Accuracy":"83.5"},"paper_url":"https://arxiv.org/abs/2204.03957v1","paper_title":"Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition","paper_date":"2022-04-08","code_links":[{"title":"axeber01/point-tnt","url":"https://github.com/axeber01/point-tnt"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146048,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"Point-BERT","metrics":{"OBJ-BG (OA)":"87.43","OBJ-ONLY (OA)":"88.12","Overall Accuracy":"83.1"},"paper_url":"https://arxiv.org/abs/2111.14819v2","paper_title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","paper_date":"2021-11-29","code_links":[{"title":"julie-tang00/point-bert","url":"https://github.com/julie-tang00/point-bert"},{"title":"lulutang0608/Point-BERT","url":"https://github.com/lulutang0608/Point-BERT"},{"title":"lmd0311/pointmamba","url":"https://github.com/lmd0311/pointmamba"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":146049,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"MVTN","metrics":{"OBJ-BG (OA)":"92.6","OBJ-ONLY (OA)":"92.3","Overall Accuracy":"82.8"},"paper_url":"https://arxiv.org/abs/2011.13244v3","paper_title":"MVTN: Multi-View Transformation Network for 3D Shape Recognition","paper_date":"2020-11-26","code_links":[{"title":"ajhamdi/MVTN","url":"https://github.com/ajhamdi/MVTN"},{"title":"ajhamdi/mvtorch","url":"https://github.com/ajhamdi/mvtorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146050,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PRA-Net","metrics":{"Mean Accuracy":"79.1","Overall Accuracy":"82.1"},"paper_url":"https://arxiv.org/abs/2112.04903v1","paper_title":"PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis","paper_date":"2021-12-09","code_links":[{"title":"xiwuchen/pra-net","url":"https://github.com/xiwuchen/pra-net"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146051,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DynamicScale","metrics":{"Overall Accuracy":"82.0"},"paper_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9565556","paper_title":"Dynamic Local Geometry Capture in 3D PointCloud Classification","paper_date":"2021-10-19","code_links":[{"title":"VimsLab/DynamicScale","url":"https://github.com/VimsLab/DynamicScale"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146052,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PatchAugment","metrics":{"Mean Accuracy":"79.7","Overall Accuracy":"81.0"},"paper_url":"https://openaccess.thecvf.com/content/ICCV2021W/DLGC/html/Sheshappanavar_PatchAugment_Local_Neighborhood_Augmentation_in_Point_Cloud_Classification_ICCVW_2021_paper.html","paper_title":"PatchAugment: Local Neighborhood Augmentation in Point Cloud Classification","paper_date":"2021-10-19","code_links":[{"title":"VimsLab/PatchAugment","url":"https://github.com/VimsLab/PatchAugment"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146053,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"GBNet","metrics":{"Mean Accuracy":"77.8","Overall Accuracy":"80.5"},"paper_url":"https://arxiv.org/abs/1911.12885v5","paper_title":"Geometric Back-projection Network for Point Cloud Classification","paper_date":"2019-11-28","code_links":[{"title":"ShiQiu0419/GFNet","url":"https://github.com/ShiQiu0419/GFNet"},{"title":"ShiQiu0419/GBNet","url":"https://github.com/ShiQiu0419/GBNet"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146054,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"SimpleView","metrics":{"Overall Accuracy":"80.5"},"paper_url":"https://openreview.net/forum?id=XwATtbX3oCz","paper_title":"Revisiting Point Cloud Classification with a Simple and Effective Baseline","paper_date":"2021-01-01","code_links":[{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"IsaacCorley/simpleview-pytorch","url":"https://github.com/IsaacCorley/simpleview-pytorch"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146055,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DRNet","metrics":{"Mean Accuracy":"78.0","Overall Accuracy":"80.3"},"paper_url":"https://arxiv.org/abs/2005.06734v2","paper_title":"Dense-Resolution Network for Point Cloud Classification and Segmentation","paper_date":"2020-05-14","code_links":[{"title":"ShiQiu0419/DRNet","url":"https://github.com/ShiQiu0419/DRNet"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146056,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointCNN","metrics":{"Mean Accuracy":"75.1","OBJ-BG (OA)":"86.1","OBJ-ONLY (OA)":"85.5","Overall Accuracy":"78.5"},"paper_url":"http://arxiv.org/abs/1801.07791v5","paper_title":"PointCNN: Convolution On $\\mathcal{X}$-Transformed Points","paper_date":"2018-01-23","code_links":[{"title":"pyg-team/pytorch_geometric","url":"https://github.com/pyg-team/pytorch_geometric"},{"title":"yangyanli/PointCNN","url":"https://github.com/yangyanli/PointCNN"},{"title":"luost26/diffusion-point-cloud","url":"https://github.com/luost26/diffusion-point-cloud"},{"title":"nicolas-chaulet/torch-points3d","url":"https://github.com/nicolas-chaulet/torch-points3d"},{"title":"hxdengBerkeley/PointCNN.Pytorch","url":"https://github.com/hxdengBerkeley/PointCNN.Pytorch"},{"title":"octree-nn/ocnn-pytorch","url":"https://github.com/octree-nn/ocnn-pytorch"},{"title":"agarret7/PointCNN","url":"https://github.com/agarret7/PointCNN"},{"title":"chinakook/PointCNN.MX","url":"https://github.com/chinakook/PointCNN.MX"},{"title":"lanlan96/3drm","url":"https://github.com/lanlan96/3drm"},{"title":"NMADALI97/PointCNN_Pytorch","url":"https://github.com/NMADALI97/PointCNN_Pytorch"},{"title":"LebronGG/PointCnn","url":"https://github.com/LebronGG/PointCnn"},{"title":"Lw510107/PointCNN","url":"https://github.com/Lw510107/PointCNN"},{"title":"c3210927/point_cnn","url":"https://github.com/c3210927/point_cnn"},{"title":"tch/pointcnn","url":"https://github.com/tch/pointcnn"},{"title":"dream-chaser/pointcnn_for_3DFER","url":"https://github.com/dream-chaser/pointcnn_for_3DFER"},{"title":"tschattschneider/pointcnn","url":"https://github.com/tschattschneider/pointcnn"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146057,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"DGCNN","metrics":{"Mean Accuracy":"73.6","OBJ-BG (OA)":"82.8","OBJ-ONLY (OA)":"86.2","Overall Accuracy":"78.1"},"paper_url":"https://arxiv.org/abs/1801.07829v2","paper_title":"Dynamic Graph CNN for Learning on Point Clouds","paper_date":"2018-01-24","code_links":[{"title":"WangYueFt/dgcnn","url":"https://github.com/WangYueFt/dgcnn"},{"title":"vinits5/learning3d","url":"https://github.com/vinits5/learning3d"},{"title":"AnTao97/dgcnn.pytorch","url":"https://github.com/AnTao97/dgcnn.pytorch"},{"title":"bupt-gamma/gammagl","url":"https://github.com/bupt-gamma/gammagl"},{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"hqucms/ParticleNet","url":"https://github.com/hqucms/ParticleNet"},{"title":"lingzhang1/ContrastNet","url":"https://github.com/lingzhang1/ContrastNet"},{"title":"cy-xu/spatially_aware_ai","url":"https://github.com/cy-xu/spatially_aware_ai"},{"title":"yossilevii100/refocusing","url":"https://github.com/yossilevii100/refocusing"},{"title":"yossilevii100/critical_points2","url":"https://github.com/yossilevii100/critical_points2"},{"title":"hansen7/NRS_3D","url":"https://github.com/hansen7/NRS_3D"},{"title":"brent-murray/tr3d_pointaugdgcnn","url":"https://github.com/brent-murray/tr3d_pointaugdgcnn"},{"title":"nnn911/MLSI","url":"https://github.com/nnn911/MLSI"},{"title":"lingzhang1/dgcnn_sampling","url":"https://github.com/lingzhang1/dgcnn_sampling"},{"title":"lingzhang1/dgcnn_v2","url":"https://github.com/lingzhang1/dgcnn_v2"},{"title":"xrndai/dgcnn_amino_acid_structure","url":"https://github.com/xrndai/dgcnn_amino_acid_structure"},{"title":"JingfeiHuang/DGCNN-Paddle","url":"https://github.com/JingfeiHuang/DGCNN-Paddle"},{"title":"af13s/dgcnn-amino","url":"https://github.com/af13s/dgcnn-amino"},{"title":"Squanch-U/DGCNN","url":"https://github.com/Squanch-U/DGCNN"},{"title":"AmitBracha/GIP_project","url":"https://github.com/AmitBracha/GIP_project"},{"title":"gai-shaoyan/mind3d","url":"https://gitee.com/gai-shaoyan/mind3d"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146058,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNet++","metrics":{"Mean Accuracy":"75.4","OBJ-BG (OA)":"82.3","OBJ-ONLY (OA)":"84.3","Overall Accuracy":"77.9"},"paper_url":"http://arxiv.org/abs/1706.02413v1","paper_title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","paper_date":"2017-06-07","code_links":[{"title":"yanx27/Pointnet_Pointnet2_pytorch","url":"https://github.com/yanx27/Pointnet_Pointnet2_pytorch"},{"title":"charlesq34/pointnet2","url":"https://github.com/charlesq34/pointnet2"},{"title":"facebookresearch/votenet","url":"https://github.com/facebookresearch/votenet"},{"title":"erikwijmans/Pointnet2_PyTorch","url":"https://github.com/erikwijmans/Pointnet2_PyTorch"},{"title":"rusty1s/pytorch_cluster","url":"https://github.com/rusty1s/pytorch_cluster"},{"title":"sshaoshuai/Pointnet2.PyTorch","url":"https://github.com/sshaoshuai/Pointnet2.PyTorch"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/pointnet2"},{"title":"zaiweizhang/H3DNet","url":"https://github.com/zaiweizhang/H3DNet"},{"title":"hehefan/P4Transformer","url":"https://github.com/hehefan/P4Transformer"},{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"thu17cyz/3DIoUMatch","url":"https://github.com/thu17cyz/3DIoUMatch"},{"title":"hehefan/PointRNN","url":"https://github.com/hehefan/PointRNN"},{"title":"facebookresearch/imvotenet","url":"https://github.com/facebookresearch/imvotenet"},{"title":"referit3d/referit3d","url":"https://github.com/referit3d/referit3d"},{"title":"hehefan/Point-Spatio-Temporal-Convolution","url":"https://github.com/hehefan/Point-Spatio-Temporal-Convolution"},{"title":"dgriffiths3/pointnet2-tensorflow2","url":"https://github.com/dgriffiths3/pointnet2-tensorflow2"},{"title":"nickgkan/beauty_detr","url":"https://github.com/nickgkan/beauty_detr"},{"title":"nickgkan/butd_detr","url":"https://github.com/nickgkan/butd_detr"},{"title":"open-air-sun/pq-transformer","url":"https://github.com/open-air-sun/pq-transformer"},{"title":"hehefan/PointRNN-PyTorch","url":"https://github.com/hehefan/PointRNN-PyTorch"},{"title":"joyhsu0504/ns3d","url":"https://github.com/joyhsu0504/ns3d"},{"title":"curryyuan/x-trans2cap","url":"https://github.com/curryyuan/x-trans2cap"},{"title":"zyang-ur/SAT","url":"https://github.com/zyang-ur/SAT"},{"title":"iballester/SPiKE","url":"https://github.com/iballester/SPiKE"},{"title":"johnsonsign/mast-pre","url":"https://github.com/johnsonsign/mast-pre"},{"title":"AsahiLiu/PointDetectron","url":"https://github.com/AsahiLiu/PointDetectron"},{"title":"hehefan/PSTNet2","url":"https://github.com/hehefan/PSTNet2"},{"title":"JohnsonSign/PointCMP","url":"https://github.com/JohnsonSign/PointCMP"},{"title":"dfki-av/mikasa-3dvg","url":"https://github.com/dfki-av/mikasa-3dvg"},{"title":"Ghailen-Ben-Achour/PointNet2_Segmentation","url":"https://github.com/Ghailen-Ben-Achour/PointNet2_Segmentation"},{"title":"houseleo/pointnet","url":"https://github.com/houseleo/pointnet"},{"title":"tao-tao-tao-tao-tao/diffusion_suction","url":"https://github.com/tao-tao-tao-tao-tao/diffusion_suction"},{"title":"Lonepic/SPIB","url":"https://github.com/Lonepic/SPIB"},{"title":"asalarpour/Point_GN","url":"https://github.com/asalarpour/Point_GN"},{"title":"LinZhuoChen/pointnet2_multi_gpu","url":"https://github.com/LinZhuoChen/pointnet2_multi_gpu"},{"title":"shaygu62/Protein-Classification","url":"https://github.com/shaygu62/Protein-Classification"},{"title":"zhh6425/LocalContextPropagation","url":"https://github.com/zhh6425/LocalContextPropagation"},{"title":"ikh-innovation/roboweldar-votenet","url":"https://github.com/ikh-innovation/roboweldar-votenet"},{"title":"witignite/Frustum-PointNet","url":"https://github.com/witignite/Frustum-PointNet"},{"title":"airalcorn2/parking-lot-pointnetplusplus","url":"https://github.com/airalcorn2/parking-lot-pointnetplusplus"},{"title":"ftdlyc/pointnet_pytorch","url":"https://github.com/ftdlyc/pointnet_pytorch"},{"title":"tingxueronghua/dpke","url":"https://github.com/tingxueronghua/dpke"},{"title":"timothylimyl/PointNet-Pytorch","url":"https://github.com/timothylimyl/PointNet-Pytorch"},{"title":"zhh6425/MotionPointNet","url":"https://github.com/zhh6425/MotionPointNet"},{"title":"alililia/ms_extend","url":"https://github.com/alililia/ms_extend/tree/main/ascend_pointnet2"},{"title":"hoangcuongbk80/VoteGrasp","url":"https://github.com/hoangcuongbk80/VoteGrasp"},{"title":"2024-MindSpore-1/Code4","url":"https://github.com/2024-MindSpore-1/Code4/tree/main/PointNet2"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/PointNet2"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/PointNet"},{"title":"alililia/ms_extend","url":"https://github.com/alililia/ms_extend/tree/main/gpu_pointnet2"},{"title":"tonysy/pointnet2_tf","url":"https://github.com/tonysy/pointnet2_tf"},{"title":"Xiangxu-0103/Octant-CNN","url":"https://github.com/Xiangxu-0103/Octant-CNN"},{"title":"Lw510107/PointNet","url":"https://github.com/Lw510107/PointNet"},{"title":"xurui1217/pointnet2-master","url":"https://github.com/xurui1217/pointnet2-master"},{"title":"SY-Xuan/pointnet_plus_plus_paddlepaddle","url":"https://github.com/SY-Xuan/pointnet_plus_plus_paddlepaddle"},{"title":"LONG-9621/VoteNet","url":"https://github.com/LONG-9621/VoteNet"},{"title":"LONG-9621/PointNet-","url":"https://github.com/LONG-9621/PointNet-"},{"title":"Harut0726/votenet","url":"https://github.com/Harut0726/votenet"},{"title":"FlowWind1999/pointnet-2","url":"https://github.com/FlowWind1999/pointnet-2"},{"title":"llzlcl/pointcloud-segment","url":"https://github.com/llzlcl/pointcloud-segment"},{"title":"zenroad/modifypointnet","url":"https://github.com/zenroad/modifypointnet"},{"title":"caizeyu1992/pointnet2","url":"https://github.com/caizeyu1992/pointnet2"},{"title":"2023-MindSpore-1/ms-code-8","url":"https://github.com/2023-MindSpore-1/ms-code-8/tree/main/PointNet2"},{"title":"gai-shaoyan/mind3d","url":"https://gitee.com/gai-shaoyan/mind3d"},{"title":"2023-MindSpore-1/ms-code-223","url":"https://github.com/2023-MindSpore-1/ms-code-223/tree/main/PointNet"},{"title":"MindSpore-paper-code-3/code4","url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/frustum-pointnet"},{"title":"2023-MindSpore-1/ms-code-223","url":"https://github.com/2023-MindSpore-1/ms-code-223/tree/main/PointNet2"},{"title":"brbzjl/pointnet2","url":"https://github.com/brbzjl/pointnet2"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146059,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"SpiderCNN","metrics":{"Mean Accuracy":"69.8","Overall Accuracy":"73.7"},"paper_url":"http://arxiv.org/abs/1803.11527v3","paper_title":"SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters","paper_date":"2018-03-30","code_links":[{"title":"xyf513/SpiderCNN","url":"https://github.com/xyf513/SpiderCNN"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146060,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"PointNet","metrics":{"Mean Accuracy":"63.4","Overall Accuracy":"68.2"},"paper_url":"http://arxiv.org/abs/1612.00593v2","paper_title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","paper_date":"2016-12-02","code_links":[{"title":"charlesq34/pointnet","url":"https://github.com/charlesq34/pointnet"},{"title":"fxia22/pointnet.pytorch","url":"https://github.com/fxia22/pointnet.pytorch"},{"title":"WangYueFt/dgcnn","url":"https://github.com/WangYueFt/dgcnn"},{"title":"vinits5/learning3d","url":"https://github.com/vinits5/learning3d"},{"title":"DylanWusee/pointconv_pytorch","url":"https://github.com/DylanWusee/pointconv_pytorch"},{"title":"nikitakaraevv/pointnet","url":"https://github.com/nikitakaraevv/pointnet"},{"title":"maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification","url":"https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification"},{"title":"princeton-vl/SimpleView","url":"https://github.com/princeton-vl/SimpleView"},{"title":"sarthakTUM/roofn3d","url":"https://github.com/sarthakTUM/roofn3d"},{"title":"jtpils/treegan","url":"https://github.com/jtpils/treegan"},{"title":"ajhamdi/AdvPC","url":"https://github.com/ajhamdi/AdvPC"},{"title":"soumik12345/point-cloud-segmentation","url":"https://github.com/soumik12345/point-cloud-segmentation"},{"title":"AI-Guru/pointcloud_experiments","url":"https://github.com/AI-Guru/pointcloud_experiments"},{"title":"ali-stanford/pointnetcfd","url":"https://github.com/ali-stanford/pointnetcfd"},{"title":"romaintha/pytorch_pointnet","url":"https://github.com/romaintha/pytorch_pointnet"},{"title":"saaries/PointNet","url":"https://github.com/saaries/PointNet"},{"title":"Fragjacker/Pointcloud-grad-CAM","url":"https://github.com/Fragjacker/Pointcloud-grad-CAM"},{"title":"ZhihaoZhu/PointNet-Implementation-Tensorflow","url":"https://github.com/ZhihaoZhu/PointNet-Implementation-Tensorflow"},{"title":"YanWei123/Pytorch-implementation-of-FoldingNet-encoder-and-decoder-with-graph-pooling-covariance-add-quanti","url":"https://github.com/YanWei123/Pytorch-implementation-of-FoldingNet-encoder-and-decoder-with-graph-pooling-covariance-add-quanti"},{"title":"Yuto0107/pointnet","url":"https://github.com/Yuto0107/pointnet"},{"title":"YanWei123/PointNet-encoder-and-FoldingNet-decoder-add-quantization-change-latent-code-size-from-512-to-1024","url":"https://github.com/YanWei123/PointNet-encoder-and-FoldingNet-decoder-add-quantization-change-latent-code-size-from-512-to-1024"},{"title":"opeco17/pointnet","url":"https://github.com/opeco17/pointnet"},{"title":"Dir-b/PointNet","url":"https://github.com/Dir-b/PointNet"},{"title":"Young98CN/pointconv_pytorch","url":"https://github.com/Young98CN/pointconv_pytorch"},{"title":"y2kmz/pointnetv2","url":"https://github.com/y2kmz/pointnetv2"},{"title":"YanWei123/Pointnet_encoder_Foldingnet_decoder_quantization","url":"https://github.com/YanWei123/Pointnet_encoder_Foldingnet_decoder_quantization"},{"title":"imanlab/deep_movement_primitives","url":"https://github.com/imanlab/deep_movement_primitives"},{"title":"abdullahozer11/Segmentation-and-Classification-of-Objects-in-Point-Clouds","url":"https://github.com/abdullahozer11/Segmentation-and-Classification-of-Objects-in-Point-Clouds"},{"title":"donshen/pointnet.phasedetection","url":"https://github.com/donshen/pointnet.phasedetection"},{"title":"ModelBunker/PointNet-TensorFlow","url":"https://github.com/ModelBunker/PointNet-TensorFlow"},{"title":"amyllykoski/CycleGAN","url":"https://github.com/amyllykoski/CycleGAN"},{"title":"Javed002/Object_detection_PointNet","url":"https://github.com/Javed002/Object_detection_PointNet"},{"title":"sanantoniochili/PointCloud_KNN","url":"https://github.com/sanantoniochili/PointCloud_KNN"},{"title":"PaParaZz1/PointNet","url":"https://github.com/PaParaZz1/PointNet"},{"title":"yevgm/deepadv3d","url":"https://github.com/yevgm/deepadv3d"},{"title":"witignite/Frustum-PointNet","url":"https://github.com/witignite/Frustum-PointNet"},{"title":"m-117/PointNet-ein-Implementationsbeispiel-mit-Jupyter-Notebooks","url":"https://github.com/m-117/PointNet-ein-Implementationsbeispiel-mit-Jupyter-Notebooks"},{"title":"alpemek/ais3d","url":"https://github.com/alpemek/ais3d"},{"title":"yanxp/PointNet","url":"https://github.com/yanxp/PointNet"},{"title":"ftdlyc/pointnet_pytorch","url":"https://github.com/ftdlyc/pointnet_pytorch"},{"title":"Melo-Wang/Deep-Learning-on-Point-Cloud-of-Aerospace-Components-for-3D-Classification","url":"https://github.com/Melo-Wang/Deep-Learning-on-Point-Cloud-of-Aerospace-Components-for-3D-Classification"},{"title":"Phimos/Paddle-PointNet","url":"https://github.com/Phimos/Paddle-PointNet"},{"title":"zgx0534/pointnet_win","url":"https://github.com/zgx0534/pointnet_win"},{"title":"timothylimyl/PointNet-Pytorch","url":"https://github.com/timothylimyl/PointNet-Pytorch"},{"title":"minhncedutw/pointnet1_keras","url":"https://github.com/minhncedutw/pointnet1_keras"},{"title":"Jagyan/ghost_radarpoint_detection","url":"https://github.com/Jagyan/ghost_radarpoint_detection"},{"title":"brendanmallery9/entropic-barycenters","url":"https://github.com/brendanmallery9/entropic-barycenters"},{"title":"2024-MindSpore-1/Code4","url":"https://github.com/2024-MindSpore-1/Code4/tree/main/PointNet"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/frustum-pointnet"},{"title":"xiuyu0000/vision","url":"https://github.com/xiuyu0000/vision/blob/main/mindvision/ms3d/models/pointnet2cls.py"},{"title":"hnmspirit/pointnet1","url":"https://github.com/hnmspirit/pointnet1"},{"title":"yangyucheng000/pointnet","url":"https://github.com/yangyucheng000/pointnet"},{"title":"eth212/Qmind_ModelNet10_PointNet","url":"https://github.com/eth212/Qmind_ModelNet10_PointNet"},{"title":"smfirmin/DeepLearningFinalProject","url":"https://github.com/smfirmin/DeepLearningFinalProject"},{"title":"ECE685-FinalProject/3D-object-recognition","url":"https://github.com/ECE685-FinalProject/3D-object-recognition"},{"title":"KhusDM/PointNetTree","url":"https://github.com/KhusDM/PointNetTree"},{"title":"Lw510107/pointnet-2018.6.27-","url":"https://github.com/Lw510107/pointnet-2018.6.27-"},{"title":"xurui1217/pointnet.pytorch-master","url":"https://github.com/xurui1217/pointnet.pytorch-master"},{"title":"hnVfly/pointnet.mxnet","url":"https://github.com/hnVfly/pointnet.mxnet"},{"title":"LebronGG/PointNet","url":"https://github.com/LebronGG/PointNet"},{"title":"GOD-GOD-Autonomous-Vehicle/self-pointnet","url":"https://github.com/GOD-GOD-Autonomous-Vehicle/self-pointnet"},{"title":"AlfredoZermini/PointNet","url":"https://github.com/AlfredoZermini/PointNet"},{"title":"wonderland-dsg/pointnet-grid","url":"https://github.com/wonderland-dsg/pointnet-grid"},{"title":"aviros/roatationPointnet","url":"https://github.com/aviros/roatationPointnet"},{"title":"THHHomas/mls","url":"https://github.com/THHHomas/mls"},{"title":"liuch37/pointnet","url":"https://github.com/liuch37/pointnet"},{"title":"yanx27/Pointnet","url":"https://github.com/yanx27/Pointnet"},{"title":"Taeuk-Jang/pointcompletion","url":"https://github.com/Taeuk-Jang/pointcompletion"},{"title":"ytng001/sensemaking","url":"https://github.com/ytng001/sensemaking"},{"title":"nddoshi/pointnet","url":"https://github.com/nddoshi/pointnet"},{"title":"SY-Xuan/pointnet_paddle","url":"https://github.com/SY-Xuan/pointnet_paddle"},{"title":"Cmeijiang/PointNet_MS","url":"https://github.com/Cmeijiang/PointNet_MS"},{"title":"AndreiMoraru123/PointNet","url":"https://github.com/AndreiMoraru123/PointNet"},{"title":"mengxingshifen1218/pointnet.pytorch","url":"https://github.com/mengxingshifen1218/pointnet.pytorch"},{"title":"Moon-Xuezha/PointNet","url":"https://github.com/Moon-Xuezha/PointNet"},{"title":"ajertec/PointNetKeras","url":"https://github.com/ajertec/PointNetKeras"},{"title":"2023-MindSpore-1/ms-code-35","url":"https://github.com/2023-MindSpore-1/ms-code-35"},{"title":"LONG-9621/Extract_Point_3D","url":"https://github.com/LONG-9621/Extract_Point_3D"},{"title":"Mind23-2/MindCode-63","url":"https://github.com/Mind23-2/MindCode-63"},{"title":"merazlab/3D_Deep_Learning_Link","url":"https://github.com/merazlab/3D_Deep_Learning_Link"},{"title":"2023-MindSpore-1/ms-code-7","url":"https://github.com/2023-MindSpore-1/ms-code-7/tree/main/PointNet"},{"title":"KaidongLi/tf-3d-alpha","url":"https://github.com/KaidongLi/tf-3d-alpha"},{"title":"gai-shaoyan/mind3d","url":"https://gitee.com/gai-shaoyan/mind3d"},{"title":"prasadsawant5/PointNet","url":"https://github.com/prasadsawant5/PointNet"},{"title":"SonuDileep/3-D-Object-Detection-using-PointNet","url":"https://github.com/SonuDileep/3-D-Object-Detection-using-PointNet"},{"title":"BPMJG/annotated_pointnet","url":"https://github.com/BPMJG/annotated_pointnet"},{"title":"debajyotid2/pointnet_pl","url":"https://github.com/debajyotid2/pointnet_pl"},{"title":"SBPL-Cruz/perch_pose_sampler","url":"https://github.com/SBPL-Cruz/perch_pose_sampler"},{"title":"2023-MindSpore-4/Code9","url":"https://github.com/2023-MindSpore-4/Code9/tree/main/PointNet"},{"title":"wuryantoAji/POINTNET","url":"https://github.com/wuryantoAji/POINTNET"},{"title":"LONG-9621/PointNet","url":"https://github.com/LONG-9621/PointNet"},{"title":"bt77/pointnet","url":"https://github.com/bt77/pointnet"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/PointNet2"},{"title":"KiranAkadas/My_Pointnet_v2","url":"https://github.com/KiranAkadas/My_Pointnet_v2"},{"title":"YiruS/pointnet_adversarial","url":"https://github.com/YiruS/pointnet_adversarial"},{"title":"Harut0726/my-pointnet-tensorflow","url":"https://github.com/Harut0726/my-pointnet-tensorflow"},{"title":"AlvesRobot/Deep-Learning-on-Point-Cloud-for-3D-Classification-and-Segmentation","url":"https://github.com/AlvesRobot/Deep-Learning-on-Point-Cloud-for-3D-Classification-and-Segmentation"},{"title":"hz-ants/pointnet.pytorch","url":"https://github.com/hz-ants/pointnet.pytorch"},{"title":"VaanHUANG/CSCI5210HW1","url":"https://github.com/VaanHUANG/CSCI5210HW1"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/PointNet"},{"title":"ShadowShadowWong/update-pointnet-work","url":"https://github.com/ShadowShadowWong/update-pointnet-work"},{"title":"Yang2446/pointnet","url":"https://github.com/Yang2446/pointnet"},{"title":"lingzhang1/pointnet_pytorch","url":"https://github.com/lingzhang1/pointnet_pytorch"},{"title":"dwtstore/sfm1","url":"https://github.com/dwtstore/sfm1"},{"title":"freddieee/pn_6d_single","url":"https://github.com/freddieee/pn_6d_single"},{"title":"ahmed-anas/thesis-pointnet","url":"https://github.com/ahmed-anas/thesis-pointnet"},{"title":"coconutzs/PointNet_zs","url":"https://github.com/coconutzs/PointNet_zs"},{"title":"CheesyB/cpointnet","url":"https://github.com/CheesyB/cpointnet"},{"title":"lingzhang1/pointnet_tensorflow","url":"https://github.com/lingzhang1/pointnet_tensorflow"},{"title":"aviros/pointnet_totations","url":"https://github.com/aviros/pointnet_totations"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146061,"task":"3D Point Cloud Classification","parent_task":"3D Point Cloud Reconstruction","dataset":"ScanObjectNN","model_name":"ExpPoint-MAE","metrics":{"OBJ-BG (OA)":"90.88","OBJ-ONLY (OA)":"90.02"},"paper_url":"https://arxiv.org/abs/2306.10798v3","paper_title":"ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformers","paper_date":"2023-06-19","code_links":[{"title":"vvrpanda/exppoint-mae","url":"https://github.com/vvrpanda/exppoint-mae"}],"metrics_order":"[\"Overall Accuracy\", \"Mean Accuracy\", \"OBJ-BG (OA)\", \"OBJ-ONLY (OA)\", \"FLOPs\", \"Number of params\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]}]}