| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| 3D Visual Grounding | Nr3D (test) | Overall Success Rate76.1 | 88 | |
| 3D Visual Grounding | Nr3D | Overall Success Rate69.9 | 74 | |
| 3D Dense Captioning | Nr3D 1 (val) | CIDEr (IoU=0.5)54.45 | 22 | |
| 3D Visual Grounding | Nr3D (val) | Easy Score70.2 | 13 | |
| 3D Dense Captioning | Nr3D (test) | C Score @ 0.5 IoU59.48 | 13 | |
| Oracle 3D Dense Captioning | Nr3D (val) | CIDEr85.4 | 10 | |
| 3D dense captioning | Nr3D | C Score (0.5 IoU)37.37 | 9 | |
| 3D Dense Captioning | Nr3D 1 (test) | CIDEr52.84 | 7 | |
| 3D Referring Expression Comprehension | NR3D constrained subset ReferIt3D (test) | Overall Accuracy52.6 | 5 | |
| 3D Scene Question Answering | Nr3D | Similarity Score50.6 | 3 |