3D Object Classification on ScanNet real-world scene-level v2
49.4Average ScoreTAMM
Evaluation results
| Method | Links | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| TAMMzero-shot=true, 3D Encoder=Point-BERT [54], Pre-trained dataset=Ensembled dataset2024.02 | 49.4 | 66.7 | 4.8 | 83.6 | 84.5 | 48.9 | 57.9 | 48.2 | 80.5 | 61.3 | 1.9 | 60.6 | 83.6 | 7 | 41.4 | 56.1 | 48.4 | 3.6 | |
| OpenShapezero-shot=true, 3D Encoder=Point-BERT [54], Pre-trained dataset=Ensembled dataset2024.02 | 45.6 | 66.7 | 3.2 | 75.8 | 83.5 | 37.7 | 49.2 | 47.5 | 64.9 | 48.2 | 1.9 | 66.1 | 70.2 | 1.8 | 50 | 57.1 | 45.2 | 7.1 | |
| CLIPzero-shot=true2024.02 | 38.5 | 32.6 | 67.2 | 69.3 | 42.3 | 18.3 | 19.1 | 4 | 62.6 | 1.4 | 12.7 | 52.8 | 40.1 | 9.1 | 59.7 | 41 | 71 | 45.5 | |
| CLIP2Pointzero-shot=true, Use real-world data (TP)=true2024.02 | 35.2 | 11.8 | 3 | 45.1 | 27.6 | 10.5 | 61.5 | 2.6 | 71.9 | 0.3 | 33.6 | 29.9 | 4.7 | 11.5 | 72.2 | 92.4 | 86.1 | 34 | |
| PointCLIPzero-shot=true, Use real-world data (TP)=true2024.02 | 26.1 | 0 | 55.7 | 72.8 | 5 | 5.1 | 1.7 | 0 | 77.2 | 0 | 0 | 51.7 | 0.3 | 0 | 0 | 40.3 | 85.3 | 49.2 | |
| CLIP2Pointzero-shot=true2024.02 | 24.9 | 20.8 | 0 | 85.1 | 43.3 | 26.5 | 69.9 | 0 | 20.9 | 1.7 | 31.7 | 27 | 0 | 1.6 | 46.5 | 0 | 22.4 | 25.6 |