{"task":"3D Point Cloud Linear Classification","dataset":"ModelNet40","metric_names":["Overall Accuracy"],"rows":[{"id":127362,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"Point-JEPA","metrics":{"Overall Accuracy":"93.7±0.2"},"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\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":127363,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"ReCon++","metrics":{"Overall Accuracy":"93.6"},"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\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127364,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"I2P-MAE","metrics":{"Overall Accuracy":"93.4"},"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\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":127365,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"ReCon","metrics":{"Overall Accuracy":"93.4"},"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\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":127366,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"Point-M2AE","metrics":{"Overall Accuracy":"92.9"},"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\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":127367,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"IAE (DGCNN)","metrics":{"Overall Accuracy":"92.1"},"paper_url":"https://arxiv.org/abs/2201.00785v5","paper_title":"Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning","paper_date":"2022-01-03","code_links":[{"title":"simingyan/iae","url":"https://github.com/simingyan/iae"}],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":127368,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"AdaCrossNet","metrics":{"Overall Accuracy":"91.8"},"paper_url":"https://inass.org/wp-content/uploads/2024/10/2025022911-2.pdf","paper_title":"AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud Learning","paper_date":"2025-01-02","code_links":[{"title":"virgantara/AdaCrossNet","url":"https://github.com/virgantara/AdaCrossNet"}],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":127369,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"CrossMoCo","metrics":{"Overall Accuracy":"91.49"},"paper_url":"https://ieeexplore.ieee.org/abstract/document/10229841","paper_title":"CrossMoCo: Multi-modal Momentum Contrastive Learning for Point Cloud","paper_date":"2023-06-08","code_links":[{"title":"snehaputul/CrossMoCo","url":"https://github.com/snehaputul/CrossMoCo"}],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127370,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"CrossPoint","metrics":{"Overall Accuracy":"91.2"},"paper_url":"https://arxiv.org/abs/2203.00680v3","paper_title":"CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding","paper_date":"2022-03-01","code_links":[{"title":"mohamedafham/crosspoint","url":"https://github.com/mohamedafham/crosspoint"}],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":127371,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"STRL","metrics":{"Overall Accuracy":"90.9"},"paper_url":"https://arxiv.org/abs/2109.00179v1","paper_title":"Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds","paper_date":"2021-09-01","code_links":[{"title":"yichen928/STRL","url":"https://github.com/yichen928/STRL"}],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127372,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"PSG-Net","metrics":{"Overall Accuracy":"90.9"},"paper_url":"https://arxiv.org/abs/2112.05213v1","paper_title":"Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning","paper_date":"2021-12-09","code_links":[],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127373,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"PointOE","metrics":{"Overall Accuracy":"90.7"},"paper_url":"https://arxiv.org/abs/2008.00305v2","paper_title":"Self-supervised Learning of Point Clouds via Orientation Estimation","paper_date":"2020-08-01","code_links":[{"title":"OmidPoursaeed/Self_supervised_Learning_Point_Clouds","url":"https://github.com/OmidPoursaeed/Self_supervised_Learning_Point_Clouds"}],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127374,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"Point-Jigsaw","metrics":{"Overall Accuracy":"90.6"},"paper_url":"https://arxiv.org/abs/1901.08396v2","paper_title":"Self-Supervised Deep Learning on Point Clouds by Reconstructing Space","paper_date":"2019-01-24","code_links":[],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127375,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"MID-FC","metrics":{"Overall Accuracy":"90.3"},"paper_url":"https://arxiv.org/abs/2008.01068v2","paper_title":"Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination","paper_date":"2020-08-03","code_links":[{"title":"Microsoft/O-CNN","url":"https://github.com/Microsoft/O-CNN"}],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127376,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"VIP-GAN","metrics":{"Overall Accuracy":"90.2"},"paper_url":"http://arxiv.org/abs/1811.02744v1","paper_title":"View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions","paper_date":"2018-11-07","code_links":[],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127377,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"OcCo","metrics":{"Overall Accuracy":"89.2"},"paper_url":"https://arxiv.org/abs/2010.01089v3","paper_title":"Unsupervised Point Cloud Pre-Training via Occlusion Completion","paper_date":"2020-10-02","code_links":[{"title":"hansen7/OcCo","url":"https://github.com/hansen7/OcCo"}],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127378,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"FoldingNet","metrics":{"Overall Accuracy":"88.4"},"paper_url":"http://arxiv.org/abs/1712.07262v2","paper_title":"FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation","paper_date":"2017-12-19","code_links":[{"title":"AnTao97/UnsupervisedPointCloudReconstruction","url":"https://github.com/AnTao97/UnsupervisedPointCloudReconstruction"},{"title":"qinglew/FoldingNet","url":"https://github.com/qinglew/FoldingNet"},{"title":"XuyangBai/FoldingNet","url":"https://github.com/XuyangBai/FoldingNet"}],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127379,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"MAE-VAE","metrics":{"Overall Accuracy":"88.4"},"paper_url":"https://arxiv.org/abs/1907.12704v1","paper_title":"Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction","paper_date":"2019-07-30","code_links":[],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127380,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"SO-Net","metrics":{"Overall Accuracy":"87.5"},"paper_url":"http://arxiv.org/abs/1803.04249v4","paper_title":"SO-Net: Self-Organizing Network for Point Cloud Analysis","paper_date":"2018-03-12","code_links":[{"title":"lijx10/SO-Net","url":"https://github.com/lijx10/SO-Net"},{"title":"donnyruixu/pc-elm-ae","url":"https://github.com/donnyruixu/pc-elm-ae"},{"title":"LONG-9621/SO-Net","url":"https://github.com/LONG-9621/SO-Net"}],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":127381,"task":"3D Point Cloud Linear Classification","parent_task":null,"dataset":"ModelNet40","model_name":"3D-GAN","metrics":{"Overall Accuracy":"83.3"},"paper_url":"http://arxiv.org/abs/1610.07584v2","paper_title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","paper_date":"2016-10-24","code_links":[{"title":"zck119/3dgan-release","url":"https://github.com/zck119/3dgan-release"},{"title":"black0017/3D-GAN-pytorch","url":"https://github.com/black0017/3D-GAN-pytorch"},{"title":"chinokenochkan/3dgan-keras","url":"https://github.com/chinokenochkan/3dgan-keras"}],"metrics_order":"[\"Overall Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}