Semantic Scene Completion on OpenOccupancy (val)
30.2IoUJS3C-Net
Evaluation Results
| Method | Links | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| JS3C-NetInput=LiDAR (L)2024.07 | 30.2 | 12.5 | 14.2 | 3.4 | 13.6 | 12 | 7.2 | 4.3 | 7.3 | 6.8 | 9.2 | 9.1 | 27.9 | 15.3 | 14.9 | 16.2 | 14 | 24.9 | |
| LMSCNetInput=LiDAR (L)2024.07 | 27.3 | 11.5 | 12.4 | 4.2 | 12.8 | 12.1 | 6.2 | 4.7 | 6.2 | 6.3 | 8.8 | 7.2 | 24.2 | 12.3 | 16.6 | 14.1 | 13.9 | 22.2 | |
| 3DSketchInput=Monocular images with depth maps (M-D)2024.07 | 25.6 | 10.7 | 12 | 5.1 | 10.7 | 12.4 | 6.5 | 4 | 5 | 6.3 | 8 | 7.2 | 21.8 | 14.8 | 13 | 11.8 | 12 | 21.2 | |
| AICNetInput=Monocular images with depth maps (M-D)2024.07 | 23.8 | 10.6 | 11.5 | 4 | 11.8 | 12.3 | 5.1 | 3.8 | 6.2 | 6 | 8.2 | 7.5 | 24.1 | 13 | 12.8 | 11.5 | 11.6 | 20.2 | |
| HTCL-MInput=Temporal monocular images (M-T)2024.07 | 21.4 | 14.1 | 14.8 | 10.2 | 14.8 | 18.9 | 7.6 | 11.3 | 12.3 | 9.6 | 5.5 | 13.5 | 32.5 | 21.7 | 20.7 | 17.7 | 5.8 | 8.5 | |
| MonoSceneInput=Monocular images (M)2024.07 | 18.4 | 6.9 | 7.1 | 3.9 | 9.3 | 7.2 | 5.6 | 3 | 5.9 | 4.4 | 4.9 | 4.2 | 14.9 | 6.3 | 7.9 | 7.4 | 10 | 7.6 | |
| TPVFormerInput=Monocular images (M)2024.07 | 15.3 | 7.8 | 9.3 | 4.1 | 11.3 | 10.1 | 5.2 | 4.3 | 5.9 | 5.3 | 6.8 | 6.5 | 13.6 | 9 | 8.3 | 8 | 9.2 | 8.2 |