Cross-Modal Scene Retrieval (Image to Description) on 3RScan
8.72Scene Matching Recall @1Inst. Baseline
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Inst. BaselineModality Pair=I → R2025.02 | 8.72 | 40.94 | 57.05 | 69.8 | 6.38 | 38.3 | 63.83 | |
| CrossOverModality Pair=I → R2025.02 | 6.04 | 26.85 | 42.28 | 62.42 | 2.13 | 34.04 | 63.83 | |
| ULIP-2Modality Pair=I → R2025.02 | 2.01 | 4.7 | 7.38 | 14.77 | 2.13 | 6.38 | 12.77 | |
| PointBindModality Pair=I → R2025.02 | 1.34 | 4.77 | 6.71 | 13.42 | 2.13 | 6.38 | 14.89 |