Semantic Scene Completion on NYU kinect depth map (test)
0Error (Ceiling)Lin et al.
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Lin et al.training=NYU2016.11 | 0 | 11.7 | 13.3 | 14.1 | 9.4 | 29 | 24 | 6 | 7 | 16.2 | 1.1 | 12 | |
| Lin et al.2018.06 | 0 | 11.7 | 13.3 | 14.1 | 9.4 | 29 | 24 | 6 | 7 | 16.2 | 1.1 | 12 | |
| SSCNettraining=SUNCG2016.11 | 5.8 | 81.8 | 19.6 | 5.4 | 12.9 | 34.4 | 26 | 13.6 | 6.1 | 9.4 | 7.4 | 20.2 | |
| Geiger and Wangtraining=NYU2016.11 | 10.2 | 62.5 | 19.1 | 5.8 | 8.5 | 40.6 | 27.7 | 7 | 6 | 22.6 | 5.9 | 19.6 | |
| Geiger and Wang2018.06 | 10.2 | 62.5 | 19.1 | 5.8 | 8.5 | 40.6 | 27.7 | 7 | 6 | 22.6 | 5.9 | 19.6 | |
| SSCNettraining=NYU2016.11 | 15.1 | 94.7 | 24.4 | 0 | 12.6 | 32.1 | 35 | 13 | 7.8 | 27.1 | 10.1 | 24.7 | |
| SSCNettraining=SUNCG+NYU2016.11 | 15.1 | 94.6 | 24.7 | 10.8 | 17.3 | 53.2 | 45.9 | 15.9 | 13.9 | 31.1 | 12.6 | 30.5 | |
| SSCNet2018.06 | 15.1 | 94.6 | 24.7 | 10.8 | 17.3 | 53.2 | 45.9 | 15.9 | 13.9 | 31.1 | 12.6 | 30.5 | |
| SSCNet*depth-only=true2018.06 | 16.1 | 94.8 | 27 | 10.1 | 20.6 | 53.2 | 50.1 | 16.7 | 14.3 | 35.5 | 13 | 31.9 | |
| VVNet-120Backbone=1202018.06 | 19.2 | 94.4 | 27.2 | 13.8 | 19.1 | 54 | 49.3 | 17.1 | 11.2 | 35.3 | 12.4 | 32.1 | |
| VVNetR-120Backbone=R-1202018.06 | 19.3 | 94.8 | 28 | 12.2 | 19.6 | 57 | 50.5 | 17.6 | 11.9 | 35.6 | 15.3 | 32.9 | |
| VVNetR-60Backbone=R-602018.06 | 21.6 | 94.5 | 28.6 | 12.9 | 19.7 | 56.3 | 51 | 17.2 | 10.4 | 35.2 | 15.6 | 33 |