Multi3DRefer
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-object 3D Visual Grounding | Multi3DRefer | F1@0.2558.62 | 24 | |
| 3D Visual Grounding | Multi3DRefer (val) | F1@0.5054.7 | 14 | |
| 3D Visual Grounding | Multi3DRefer | Accuracy@0.2561.6 | 7 | |
| 3D Referring Segmentation | Multi3DRefer (val) | mIoU48.8 | 7 | |
| 3D Grounded Referring Expression Segmentation | Multi3DRefer v1 (test) | Acc@0.25 (ZT, with distractor)47.9 | 6 | |
| Multi-object 3D grounding | Multi3DRefer (val) | F1@0.5 (ZT, no D)94.1 | 6 | |
| 3D Visual Grounding | Multi3DRefer 62 (val) | ZT w/o D F194.1 | 5 | |
| Visual Grounding | Multi3DRefer | F1@0.554.1 | 4 | |
| 3D Visual Grounding | Multi3DRefer (test) | ZT Accuracy66.9 | 4 | |
| Multi-object grounding | Multi3DRefer (val) | F1@0.25 (ZT w/o D)82.4 | 3 |
Showing 10 of 10 rows