paper-with-me

3D Point Cloud Linear Classification 벤치마크

3D Point Cloud Linear Classification on ModelNet40

20개 결과 · ⬇ CSV · JSON

Overall Accuracy

83.3 85.9 88.5 91.1 93.7 2016-10 2026-09 3D-GAN — 83.3 (2016-10-24) FoldingNet — 88.4 (2017-12-19) SO-Net — 87.5 (2018-03-12) VIP-GAN — 90.2 (2018-11-07) Point-Jigsaw — 90.6 (2019-01-24) MAE-VAE — 88.4 (2019-07-30) PointOE — 90.7 (2020-08-01) MID-FC — 90.3 (2020-08-03) OcCo — 89.2 (2020-10-02) STRL — 90.9 (2021-09-01) PSG-Net — 90.9 (2021-12-09) IAE (DGCNN) — 92.1 (2022-01-03) CrossPoint — 91.2 (2022-03-01) Point-M2AE — 92.9 (2022-05-28) I2P-MAE — 93.4 (2022-12-13) ReCon — 93.4 (2023-02-05) CrossMoCo — 91.49 (2023-06-08) ReCon++ — 93.6 (2024-02-27) Point-JEPA — 93.7 (2024-04-25) AdaCrossNet — 91.8 (2025-01-02) 3D-GAN — 83.3 (2016-10-24) FoldingNet — 88.4 (2017-12-19) VIP-GAN — 90.2 (2018-11-07) Point-Jigsaw — 90.6 (2019-01-24) PointOE — 90.7 (2020-08-01) STRL — 90.9 (2021-09-01) IAE (DGCNN) — 92.1 (2022-01-03) Point-M2AE — 92.9 (2022-05-28) I2P-MAE — 93.4 (2022-12-13) ReCon++ — 93.6 (2024-02-27) Point-JEPA — 93.7 (2024-04-25)
RankModel Overall Accuracy Extra Training Data PaperCodeYear
1 Point-JEPA 93.7±0.2 Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud Ayumu-J-S/Point-JEPA 2024
2 ReCon++ 93.6 ShapeLLM: Universal 3D Object Understanding for Embodied Interaction qizekun/ShapeLLM · qizekun/ReCon · runpeidong/act 2024
3 I2P-MAE 93.4 Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders zrrskywalker/i2p-mae · zrrskywalker/point-m2ae 2022
3 ReCon 93.4 Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining qizekun/ReCon · runpeidong/act · aHapBean/PCP-MAE · +2 2023
5 Point-M2AE 92.9 Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training zrrskywalker/i2p-mae · zrrskywalker/point-m2ae · MindSpore-paper-code-2/code400 2022
6 IAE (DGCNN) 92.1 Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning simingyan/iae 2022
7 AdaCrossNet 91.8 AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud Learning virgantara/AdaCrossNet 2025
8 CrossMoCo 91.49 CrossMoCo: Multi-modal Momentum Contrastive Learning for Point Cloud snehaputul/CrossMoCo 2023
9 CrossPoint 91.2 CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding mohamedafham/crosspoint 2022
10 STRL 90.9 Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds yichen928/STRL 2021
10 PSG-Net 90.9 Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning 2021
12 PointOE 90.7 Self-supervised Learning of Point Clouds via Orientation Estimation OmidPoursaeed/Self_supervised_Learning_Point_Clouds 2020
13 Point-Jigsaw 90.6 Self-Supervised Deep Learning on Point Clouds by Reconstructing Space 2019
14 MID-FC 90.3 Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination Microsoft/O-CNN 2020
15 VIP-GAN 90.2 View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions 2018
16 OcCo 89.2 Unsupervised Point Cloud Pre-Training via Occlusion Completion hansen7/OcCo 2020
17 FoldingNet 88.4 FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation AnTao97/UnsupervisedPointCloudReconstruction · qinglew/FoldingNet · XuyangBai/FoldingNet 2017
17 MAE-VAE 88.4 Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction 2019
19 SO-Net 87.5 SO-Net: Self-Organizing Network for Point Cloud Analysis lijx10/SO-Net · donnyruixu/pc-elm-ae · LONG-9621/SO-Net 2018
20 3D-GAN 83.3 Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling zck119/3dgan-release · black0017/3D-GAN-pytorch · chinokenochkan/3dgan-keras 2016
1–20 / 20 페이지당 10 20 50 100