3D Point Cloud Classification on ScanObjectNN
Metric: OBJ_ONLY Accuracy(%) (higher is better)
Metric: OBJ_ONLY Accuracy(%) (higher is better)
| # | Model↕ | OBJ_ONLY Accuracy(%)▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ReCon++ | 65.4 | Yes | ShapeLLM: Universal 3D Object Understanding for ... | 2024-02-27 | Code |
| 2 | Uni3D | 65.3 | Yes | Uni3D: Exploring Unified 3D Representation at Sc... | 2023-10-10 | Code |
| 3 | TAMM-PointBERT (+dlign) | 60.5 | Yes | OpenDlign: Open-World Point Cloud Understanding ... | 2024-04-25 | Code |
| 4 | ViT-Lens | 60.1 | Yes | ViT-Lens: Initiating Omni-Modal Exploration thro... | 2023-08-20 | Code |
| 5 | OpenDlign | 59.5 | Yes | OpenDlign: Open-World Point Cloud Understanding ... | 2024-04-25 | Code |
| 6 | MixCon3D-PointBERT | 58.6 | Yes | Sculpting Holistic 3D Representation in Contrast... | 2023-11-03 | Code |
| 7 | PointCLIP V2 | 50.09 | Yes | PointCLIP V2: Prompting CLIP and GPT for Powerfu... | 2022-11-21 | Code |
| 8 | ReCon | 43.7 | Yes | Contrast with Reconstruct: Contrastive 3D Repres... | 2023-02-05 | Code |
| 9 | CLIP2Point | 30.46 | Yes | CLIP2Point: Transfer CLIP to Point Cloud Classif... | 2022-10-03 | Code |
| 10 | PointCLIP | 19.28 | Yes | PointCLIP: Point Cloud Understanding by CLIP | 2021-12-04 | Code |