| ShapeLLM: Universal 3D Object Understanding for Embodied Interaction | ✓ Link | 99.5 | 0.8 | ReCon++ | 2024-02-27 |
| Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud | ✓ Link | 99.2 | 0.8 | Point-JEPA | 2024-04-25 |
| PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders | ✓ Link | 99.1 | 0.8 | PCP-MAE | 2024-08-16 |
| PointGPT: Auto-regressively Generative Pre-training from Point Clouds | ✓ Link | 99.0 | 1.0 | PointGPT | 2023-05-19 |
| Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining | ✓ Link | 98.9 | 1.2 | ReCon | 2023-02-05 |
| 3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning | | 98.8 | 0.4 | 3D-JEPA | 2024-09-24 |
| Point2Vec for Self-Supervised Representation Learning on Point Clouds | ✓ Link | 98.7 | 1.2 | point2vec | 2023-03-29 |
| Rethinking Masked Representation Learning for 3D Point Cloud Understanding | ✓ Link | 98.7 | 1.2 | OTMae3D | 2024-12-26 |
| Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning | ✓ Link | 98.7 | 1.3 | Point-RAE | 2023-09-25 |
| Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders | ✓ Link | 98.3 | 1.3 | I2P-MAE | 2022-12-13 |
| Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training | ✓ Link | 98.3 | 1.4 | Point-M2AE | 2022-05-28 |
| Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking | ✓ Link | 98.1 | 1.4 | Point-LGMask | 2023-06-08 |
| Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning? | ✓ Link | 98.0 | 1.4 | ACT | 2022-12-16 |
| Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models | ✓ Link | 97.9 | | IDPT | 2023-04-14 |
| Masked Autoencoders for Point Cloud Self-supervised Learning | ✓ Link | 97.8 | 1.8 | Point-MAE | 2022-03-13 |
| Masked Discrimination for Self-Supervised Learning on Point Clouds | ✓ Link | 97.2 | 1.7 | MaskPoint | 2022-03-21 |
| CrossMoCo: Multi-modal Momentum Contrastive Learning for Point Cloud | ✓ Link | 96.8 | 1.7 | CrossMoCo | 2023-06-08 |
| Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling | ✓ Link | 96.3 | 2.7 | Point-BERT | 2021-11-29 |
| Unsupervised Point Cloud Pre-Training via Occlusion Completion | ✓ Link | 92.5 | 1.9 | OcCo+DGCNN | 2020-10-02 |
| Unsupervised Point Cloud Pre-Training via Occlusion Completion | ✓ Link | 92.4 | 1.6 | OcCo+PointNet | 2020-10-02 |
| GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning | ✓ Link | 82.7 | 1.3 | GPr-Net + Hyp (512) | 2023-04-12 |
| GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning | ✓ Link | 82.0 | 0.9 | GPr-Net + Hyp (1024) | 2023-04-12 |
| GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning | ✓ Link | 75.1 | 2.1 | GPr-Net + Euc (1024) | 2023-04-12 |
| GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning | ✓ Link | 75.0 | 2.4 | GPr-Net + Euc (512) | 2023-04-12 |
| Self-Supervised Few-Shot Learning on Point Clouds | ✓ Link | 68.90 | 9.4 | SSFSL+PointNet | 2020-09-29 |
| PointCNN: Convolution On X-Transformed Points | ✓ Link | 68.64 | 7.0 | PointCNN | 2018-12-01 |
| Self-Supervised Few-Shot Learning on Point Clouds | ✓ Link | 65.70 | 8.4 | SSFSL+DGCNN | 2020-09-29 |
| PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation | ✓ Link | 57.81 | 15.5 | PointNet | 2016-12-02 |
| PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space | ✓ Link | 42.39 | 14.2 | PointNet++ | 2017-06-07 |
| Dynamic Graph CNN for Learning on Point Clouds | ✓ Link | 40.8 | 14.6 | DGCNN | 2018-01-24 |