Cross-Modal Scene Retrieval (Point Cloud to Description) on 3RScan
6.71Scene Matching Recall@1CrossOver
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| CrossOverModality Pair=P → R2025.02 | 6.71 | 19.46 | 32.31 | 51.01 | 8.51 | 27.66 | 51.06 | |
| Inst. BaselineModality Pair=P → R2025.02 | 0.76 | 14.09 | 24.83 | 36.24 | 0.04 | 14.89 | 27.66 | |
| ULIP-2Modality Pair=P → R2025.02 | 0.67 | 3.36 | 6.71 | 12.75 | 2.13 | 6.38 | 6.38 | |
| PointBindModality Pair=P → R2025.02 | 0.67 | 3.36 | 6.71 | 13.42 | 2.13 | 6.38 | 6.38 |