Language-grounded 3D Semantic Segmentation on Synthetic
55.13D IoUClutt3R-Seg
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Clutt3R-SegCLIP model variant=Duoduo CLIP2026.02 | 55.1 | 24.8 | |
| Clutt3R-Seg-CLIP model variant=Standard CLIP2026.02 | 41.69 | 23.7 | |
| ConceptGraphs2026.02 | 34.9 | 91.2 | |
| GraspSplats2026.02 | 20.7 | 67.5 |