3D Point Cloud Classification on ModelNet40

333개 결과 · ⬇ CSV · JSON

Overall Accuracy

Rank	Model	Overall Accuracy	Mean Accuracy	Number of params	FLOPs	Mean class accuracy	Extra Training Data	Paper	Code	Year
1	PointGST	95.3	–	–	–	–	✓	Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning	jerryfeng2003/pointgst	2024
2	Mamba3D + Point-MAE	95.1	–	16.9M	3.9G	–	✓	Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model	xhanxu/Mamba3D	2024
3	ReCon++	95.0	–	–	–	–	✓	ShapeLLM: Universal 3D Object Understanding for Embodied Interaction	qizekun/ShapeLLM · qizekun/ReCon · runpeidong/act	2024
4	PointGPT	94.9	–	–	–	–	✓
5	point2vec	94.8	92.0	–	–	–	✓	Point2Vec for Self-Supervised Representation Learning on Point Clouds	kabouzeid/point2vec	2023
6	ULIP + PointMLP	94.7	92.4	–	–	–	✓	ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding	salesforce/ulip	2022
6	ReCon	94.7	–	–	–	–	✓	Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining	qizekun/ReCon · runpeidong/act · aHapBean/PCP-MAE · +2	2023
6	*AsymDSD-B (no voting)**	94.7	–	–	–	–	✓	Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning	RFLeijenaar/AsymDSD	2025
6	RepSurf-U	94.7	–	1.48M	0.81G	–		Surface Representation for Point Clouds	hancyran/RepSurf	2022
10	PointMLP+HyCoRe	94.5	91.9	–	–	–		Rethinking the compositionality of point clouds through regularization in the hyperbolic space	diegovalsesia/hycore	2022
10	PointMLP	94.5	91.4	–	–	–		Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework	ma-xu/pointmlp-pytorch	2022
10	Point-FEMAE	94.5	–	–	–	–	✓	Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders	zyh16143998882/aaai24-pointfemae	2023
10	OTMae3D	94.5	–	–	–	–	✓	Rethinking Masked Representation Learning for 3D Point Cloud Understanding	OpenSpaceAI/OTMae3D	2024
14	PointNet2+PointCMT	94.4	91.2	1.62M	–	–		Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis	yanx27/2dpass · zhanheshen/pointcmt	2022
14	IDPT	94.4	–	–	–	–		Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models	zyh16143998882/iccv23-idpt · zyh16143998882/IDPT · zyh16143998882/aaai24-pointfemae	2023
16	OTMae3D (w/o Voting)	94.3	–	–	–	–	✓	Rethinking Masked Representation Learning for 3D Point Cloud Understanding	OpenSpaceAI/OTMae3D	2024
17	IAE + DGCNN	94.2	91.6	–	–	–	✓	Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning	simingyan/iae	2022
17	PTv2	94.2	91.6	–	–	–		Point Transformer V2: Grouped Vector Attention and Partition-based Pooling	Pointcept/Pointcept · Pointcept/PointTransformerV2	2022
17	CurveNet	94.2	–	–	–	–		Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis	vinits5/learning3d · tiangexiang/CurveNet · RF5/CurveNet	2021
17	ExpPoint-MAE	94.2	–	–	–	–	✓	ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformers	vvrpanda/exppoint-mae	2023