Semantic Scene Completion on SemanticKITTI 1.0 (test)
29.5mIoUS3CNet
Evaluation results
| Method | Links | ||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| S3CNet2020.12 | 29.5 | 45 | 42 | 22 | 17 | 7 | 52 | 31 | 6 | 41.5 | 45 | 16 | 39 | 34 | 21 | 45 | 35 | 16 | 31 | 31 | 24 | — | |
| JS3C-Net2020.12 | 23.8 | 56 | 64 | 39 | 34 | 14 | 39.4 | 33 | 7.2 | 14 | 8 | 12 | 43 | 19 | 40 | 8 | 5 | 0 | 30 | 18 | 15 | — | |
| gjt2020.12 | 21 | 54 | 61 | 36 | 32 | 6 | 38 | 32 | 5 | 2 | 3 | 7 | 39 | 18 | 34 | 4 | 1 | 0 | 27 | 15 | 12 | — | |
| ifelse2020.12 | 18.3 | 51 | 63 | 31 | 27 | 14 | 29 | 29 | 3.9 | 0 | 0 | 0 | 40 | 21 | 34 | 0 | 0 | 0 | 25 | 19 | 6 | — | |
| jbehley2020.12 | 17.7 | 50 | 62 | 31 | 23 | 6 | 34 | 30 | 4 | 0 | 0 | 0 | 40 | 21 | 33 | 0 | 0 | 0 | 24 | 16 | 6 | — | |
| yanx272020.12 | 17 | 41 | 43 | 28 | 26 | 10 | 29 | 26 | 5 | 0 | 4 | 9 | 35 | 20 | 28 | 2 | 7 | 0 | 23 | 16 | 16 | — | |
| CGFormerInput=Stereo, Image Backbone=EfficientNetB72024.05 | 16.63 | — | 64.3 | 34.2 | 34.1 | 12.1 | 25.8 | 26.1 | 4.3 | 3.7 | 1.3 | 2.7 | 24.5 | 11.2 | 29.3 | 1.7 | 3.6 | 0.4 | 18.7 | 8.7 | 9.3 | 44.41 | |
| MonoOcc-LInput=Stereo, Image Backbone=InternImage-XL2024.05 | 15.63 | — | 59.1 | 30.9 | 27.1 | 9.8 | 22.9 | 23.9 | 7.2 | 4.5 | 2.4 | 7.7 | 25 | 9.8 | 26.1 | 2.8 | 4.7 | 0.6 | 16.9 | 7.3 | 8.4 | — | |
| StereoSceneInput=Stereo, Image Backbone=EfficientNetB72024.05 | 15.36 | — | 61.9 | 31.2 | 30.7 | 10.7 | 24.2 | 22.8 | 2.8 | 3.4 | 2.4 | 6.1 | 23.8 | 8.4 | 27 | 2.9 | 2.2 | 0.5 | 16.5 | 7 | 7.2 | 43.34 | |
| SymphonizeInput=Stereo, Image Backbone=MaskDINO2024.05 | 15.04 | — | 58.4 | 29.3 | 26.9 | 11.7 | 24.7 | 23.6 | 3.2 | 3.6 | 2.6 | 5.6 | 24.2 | 10 | 23.1 | 3.2 | 1.9 | 2 | 16.1 | 7.7 | 8 | 42.19 | |
| H2GFormer-TInput=Stereo-T, Image Backbone=ResNet502024.05 | 14.6 | — | 57.9 | 30.4 | 30 | 6.9 | 24 | 23.7 | 5.2 | 0.6 | 1.2 | 5 | 25.2 | 10.7 | 25.8 | 1.1 | 0.1 | 0 | 14.6 | 7.5 | 9.3 | 43.52 | |
| HASSC-TInput=Stereo-T, Image Backbone=ResNet502024.05 | 14.38 | — | 55.3 | 29.6 | 25.9 | 11.3 | 23.1 | 23 | 2.9 | 1.9 | 1.5 | 4.9 | 24.8 | 9.8 | 26.5 | 1.4 | 3 | 0 | 14.3 | 7 | 7.1 | 42.87 | |
| MonoOcc-SInput=Stereo, Image Backbone=ResNet502024.05 | 13.8 | — | 55.2 | 27.8 | 25.1 | 9.7 | 21.4 | 23.2 | 5.2 | 2.2 | 1.5 | 5.4 | 24 | 8.7 | 23 | 1.7 | 2 | 0.2 | 13.4 | 5.8 | 6.4 | — | |
| H2GFormer-SInput=Stereo, Image Backbone=ResNet502024.05 | 13.72 | — | 56.4 | 28.6 | 26.5 | 4.9 | 22.8 | 23.4 | 4.8 | 0.8 | 0.9 | 4.1 | 24.6 | 9.1 | 23.8 | 1.2 | 2.5 | 0.1 | 13.3 | 6.4 | 6.3 | 44.2 | |
| VoxFormer-TInput=Stereo-T, Image Backbone=ResNet502024.05 | 13.41 | — | 54.1 | 26.9 | 25.1 | 7.3 | 23.5 | 21.7 | 3.6 | 1.9 | 1.6 | 4.1 | 24.4 | 8.1 | 24.2 | 1.6 | 1.1 | 0 | 13.1 | 6.6 | 5.7 | 43.21 | |
| HASSC-SInput=Stereo, Image Backbone=ResNet502024.05 | 13.34 | — | 54.6 | 27.7 | 23.8 | 6.2 | 21.1 | 22.8 | 4.7 | 1.6 | 1 | 3.9 | 23.8 | 8.5 | 23.3 | 1.6 | 4 | 0.3 | 13.1 | 5.8 | 5.5 | 43.4 | |
| DepthSSCInput=Stereo, Image Backbone=ResNet502024.05 | 13.11 | — | 55.64 | 27.25 | 25.72 | 5.78 | 20.46 | 21.94 | 3.74 | 1.35 | 0.98 | 4.17 | 23.37 | 7.64 | 21.56 | 1.34 | 2.79 | 0.28 | 12.94 | 5.87 | 6.23 | 44.58 | |
| IAMSSCInput=Mono, Image Backbone=ResNet502024.05 | 12.37 | — | 54 | 25.5 | 24.7 | 6.9 | 19.2 | 21.3 | 3.8 | 1.1 | 0.6 | 3.9 | 22.7 | 5.8 | 19.4 | 1.5 | 2.9 | 0.5 | 11.9 | 5.3 | 4.1 | 43.74 | |
| OccFormerInput=Mono, Image Backbone=EfficientNetB72024.05 | 12.32 | — | 55.9 | 30.3 | 31.5 | 6.5 | 15.7 | 21.6 | 1.2 | 1.5 | 1.7 | 3.2 | 16.8 | 3.9 | 21.3 | 2.2 | 1.1 | 0.2 | 11.9 | 3.8 | 3.7 | 34.53 | |
| VoxFormer-SInput=Stereo, Image Backbone=ResNet502024.05 | 12.2 | — | 53.9 | 25.3 | 21.1 | 5.6 | 19.8 | 20.8 | 3.5 | 1 | 0.7 | 3.7 | 22.4 | 7.5 | 21.3 | 1.4 | 2.6 | 0.2 | 11.1 | 5.1 | 4.9 | 42.95 | |
| SurroundOccInput=Mono, Image Backbone=EfficientNetB72024.05 | 11.86 | — | 56.9 | 28.3 | 30.2 | 6.8 | 15.2 | 20.6 | 1.4 | 1.6 | 1.2 | 4.4 | 14.9 | 3.4 | 19.3 | 1.4 | 2 | 0.1 | 11.3 | 3.9 | 2.4 | 34.72 | |
| TPVFormerInput=Mono, Image Backbone=EfficientNetB72024.05 | 11.26 | — | 55.1 | 27.2 | 27.4 | 6.5 | 14.8 | 19.2 | 3.7 | 1 | 0.5 | 2.3 | 13.9 | 2.6 | 20.4 | 1.1 | 2.4 | 0.3 | 11 | 2.9 | 1.5 | 34.25 | |
| MonoSceneInput=Mono, Image Backbone=EfficientNetB72024.05 | 11.08 | — | 54.7 | 27.1 | 24.8 | 5.7 | 14.4 | 18.8 | 3.3 | 0.5 | 0.7 | 4.4 | 14.9 | 2.4 | 19.5 | 1 | 1.4 | 0.4 | 11.1 | 3.3 | 2.1 | 34.16 |