3D semantic occupancy prediction on SSCBench-KITTI-360 (test)
53.58Overall IoUSSCNet
Evaluation results
| Method | Links | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SSCNetInput=LiDAR (L)2024.12 | 53.58 | 16.95 | 31.95 | 0 | 0.17 | 10.29 | 0.58 | 0.07 | 65.7 | 17.33 | 41.24 | 3.22 | 44.41 | 6.77 | 43.72 | 28.87 | 0.78 | 0.75 | 8.6 | 0.67 | — | |
| ProOOD (+VoxDet)evaluation_mode=Single-Frame2026.04 | 48.23 | 20.27 | 28.89 | 3.77 | 7.23 | 18.83 | 6.49 | 5.83 | 62.31 | 16.23 | 40.08 | 5.36 | 43.75 | 9.29 | 38.66 | 22.51 | 17.28 | 19.42 | 10.67 | 8.25 | 11.52 | |
| VoxDetevaluation_mode=Single-Frame, reproduced_official_code=true2026.04 | 48.22 | 19.97 | 28.94 | 3.88 | 5.23 | 16.2 | 6.58 | 6.15 | 62.02 | 16.27 | 39.69 | 5.34 | 43.36 | 9.1 | 38.73 | 22.79 | 17.22 | 19.74 | 10.27 | 7.99 | 10.92 | |
| LMSCNetInput=LiDAR (L)2024.12 | 47.53 | 13.65 | 20.91 | 0 | 0 | 0.26 | 0 | 0 | 62.95 | 13.51 | 33.51 | 0.2 | 43.67 | 0.33 | 40.01 | 26.8 | 0 | 0 | 3.63 | 0 | — | |
| ProOOD (+SGN)evaluation_mode=Single-Frame2026.04 | 46.62 | 17.99 | 27.23 | 2.75 | 4.23 | 12.06 | 5.76 | 4.83 | 60.07 | 14.02 | 36.57 | 5.03 | 40.92 | 7.13 | 36.96 | 22.84 | 14.15 | 15.47 | 8.82 | 4.93 | 8.35 | |
| SGNevaluation_mode=Single-Frame2026.04 | 46.22 | 17.71 | 28.2 | 2.09 | 3.02 | 11.95 | 3.68 | 4.2 | 59.49 | 14.5 | 36.53 | 4.24 | 39.79 | 7.14 | 36.61 | 23.1 | 14.86 | 16.14 | 8.24 | 4.95 | 8.17 | |
| Symphoniesevaluation_mode=Single-Frame2026.04 | 44.12 | 18.58 | 30.02 | 1.85 | 5.9 | 25.07 | 12.06 | 8.2 | 54.94 | 13.83 | 32.76 | 6.93 | 35.11 | 8.58 | 38.33 | 11.52 | 14.01 | 9.57 | 14.44 | 11.28 | 10.84 | |
| GraphGSOccBackbone=R101, Input=C2025.06 | 40.92 | 15.58 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OccFormerInput=Camera (C)2024.12 | 40.27 | 13.81 | 22.58 | 0.66 | 0.26 | 9.89 | 3.82 | 2.77 | 54.3 | 13.44 | 31.53 | 3.55 | 36.42 | 4.8 | 31 | 19.51 | 7.77 | 8.51 | 6.95 | 4.6 | — | |
| OccFormerBackbone=R101, Input=C2025.06 | 40.27 | 13.87 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OccFormerevaluation_mode=Single-Frame2026.04 | 40.27 | 13.81 | 22.58 | 0.66 | 0.26 | 9.89 | 3.82 | 2.77 | 54.3 | 13.44 | 31.53 | 3.55 | 36.42 | 4.8 | 31 | 19.51 | 7.77 | 8.51 | 6.95 | 4.6 | 4.92 | |
| TPVFormerInput=Camera (C)2024.12 | 40.22 | 13.64 | 21.56 | 1.09 | 1.37 | 8.06 | 2.57 | 2.38 | 52.99 | 11.99 | 31.07 | 3.78 | 34.83 | 4.8 | 30.08 | 17.51 | 7.46 | 5.86 | 5.48 | 2.7 | — | |
| TPVFormerBackbone=R101, Input=C2025.06 | 40.22 | 13.64 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TPVFormerevaluation_mode=Single-Frame2026.04 | 40.22 | 13.64 | 21.56 | 1.09 | 1.37 | 8.06 | 2.57 | 2.38 | 52.99 | 11.99 | 31.07 | 3.78 | 34.83 | 4.8 | 30.08 | 17.52 | 7.46 | 5.86 | 5.48 | 2.7 | 4.13 | |
| VoxformerInput=Camera (C)2024.12 | 38.76 | 11.91 | 17.84 | 1.16 | 0.89 | 4.56 | 2.06 | 1.63 | 47.01 | 9.67 | 27.21 | 2.89 | 31.18 | 4.97 | 28.99 | 14.69 | 6.51 | 6.92 | 3.79 | 2.43 | — | |
| VoxFormerevaluation_mode=Single-Frame2026.04 | 38.76 | 11.91 | 17.84 | 1.16 | 0.89 | 4.56 | 2.06 | 1.63 | 47.01 | 9.67 | 27.21 | 2.89 | 31.18 | 4.97 | 28.99 | 14.69 | 6.51 | 6.92 | 3.79 | 2.43 | 3.44 | |
| GaussianFormer-2Input=Camera (C)2024.12 | 38.37 | 13.9 | 21.08 | 2.55 | 4.21 | 12.41 | 5.73 | 1.59 | 54.12 | 11.04 | 32.31 | 3.34 | 32.01 | 4.98 | 28.94 | 17.33 | 3.57 | 5.48 | 5.88 | 3.54 | — | |
| GaussianFormer-2Backbone=R101, Input=C2025.06 | 38.37 | 13.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MonoSceneInput=Camera (C)2024.12 | 37.87 | 12.31 | 19.34 | 0.43 | 0.58 | 8.02 | 2.03 | 0.86 | 48.35 | 11.38 | 28.13 | 3.22 | 32.89 | 3.53 | 26.15 | 16.75 | 6.92 | 5.67 | 4.2 | 3.09 | — | |
| MonoSceneBackbone=R101, Input=C2025.06 | 37.87 | 12.31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MonoSceneevaluation_mode=Single-Frame2026.04 | 37.87 | 12.31 | 19.34 | 0.43 | 0.58 | 8.02 | 2.03 | 0.86 | 48.35 | 11.38 | 28.13 | 3.32 | 32.89 | 3.53 | 26.15 | 16.75 | 6.92 | 5.67 | 4.2 | 3.09 | 3.61 | |
| GaussianFormerInput=Camera (C)2024.12 | 35.38 | 12.92 | 18.93 | 1.02 | 4.62 | 18.07 | 7.59 | 3.35 | 45.47 | 10.89 | 25.03 | 5.32 | 28.44 | 5.68 | 29.54 | 8.62 | 2.99 | 2.32 | 9.51 | 5.14 | — | |
| GaussianFormerBackbone=R101, Input=C2025.06 | 35.38 | 12.92 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| VoxformerBackbone=R101, Input=C2025.06 | 18.76 | 11.91 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |