| Paper | Code | Top-1 IoU | Top-3 IoU | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation | ✓ Link | 0.525 | 0.762 | DITR | 2025-03-24 |
| Sonata: Self-Supervised Learning of Reliable Point Representations | ✓ Link | 0.495 | 0.735 | Sonata | 2025-03-20 |
| Point Transformer V3: Simpler, Faster, Stronger | ✓ Link | 0.488 | 0.725 | PTv3 | 2023-12-15 |
| Learning Context-aware Classifier for Semantic Segmentation | ✓ Link | 0.483 | 0.712 | CAC | 2023-03-21 |
| OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation | ✓ Link | 0.470 | 0.726 | OA-CNN | 2024-03-21 |
| OctFormer: Octree-based Transformers for 3D Point Clouds | ✓ Link | 0.460 | 0.691 | OctFormer | 2023-05-04 |
| 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks | ✓ Link | 0.456 | 0.683 | SpUNet (MinkowskiNet) | 2019-04-18 |
| Point Transformer V2: Grouped Vector Attention and Partition-based Pooling | ✓ Link | 0.445 | 0.688 | PTv2 | 2022-10-11 |