3D Semantic Occupancy Prediction on nuScenes-Occupancy (val)
28.1mIoUUnsOcc
Evaluation results
| Method | Links | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| UnsOccModality=C&L2026.06 | 28.1 | 29.8 | 18.2 | 34.5 | 37.2 | 18.2 | 22.1 | 21.6 | 22.7 | 22 | 29.9 | 42.6 | 26.1 | 29.2 | 28.4 | 28.6 | 38.1 | — | — | — | |
| Co-OccModality=C&L2026.06 | 27.1 | 28.1 | 16.1 | 34 | 37.7 | 17 | 21.6 | 20.8 | 15.9 | 21.9 | 28.7 | 42.3 | 25.4 | 29.1 | 28.6 | 28.2 | 38 | — | — | — | |
| M-CONetModality=C&L2026.06 | 24.7 | 24.8 | 13 | 31.6 | 34.8 | 14.6 | 18 | 20 | 14.7 | 20 | 26.6 | 39.2 | 22.8 | 26.1 | 26 | 26 | 37.1 | — | — | — | |
| DRVRModality=LiDAR, Multi-sweep point clouds=false2026.06 | 21.3 | 22.1 | 13.5 | 22.1 | 24.4 | 13.2 | 20.9 | 25.6 | 14.5 | 15.5 | 20.8 | 31.2 | 19.3 | 22.6 | 22.8 | 24.4 | 27.6 | 30.6 | — | — | |
| DRVRModality=LiDAR, #Params.=19.67M, Inference time=128.03ms2026.06 | 21.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 30.6 | — | — | |
| SurroundOccModality=C2026.06 | 20.3 | 20.5 | 11.6 | 28.1 | 30.8 | 10.7 | 15.1 | 14 | 12 | 14.3 | 22.2 | 37.2 | 23.7 | 24.4 | 22.7 | 14.8 | 21.8 | — | — | — | |
| OccFormerModality=C2026.06 | 20.1 | 21.1 | 11.3 | 28.2 | 30.3 | 10.6 | 15.7 | 14.4 | 11.2 | 14 | 22.6 | 37.3 | 22.4 | 24.9 | 23.5 | 15.2 | 21.1 | — | — | — | |
| OmniNWMCategory=Generative, Input=Camera2025.10 | 19.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 33.3 | — | — | |
| FB-OccModality=C2026.06 | 19.6 | 20.6 | 11.3 | 26.9 | 29.8 | 10.4 | 13.6 | 13.7 | 11.4 | 11.5 | 20.6 | 38.2 | 21.5 | 24.6 | 22.7 | 14.8 | 21.6 | — | — | — | |
| RenderOccModality=C2026.06 | 19 | 19.7 | 11.2 | 28.1 | 28.2 | 9.8 | 14.7 | 11.8 | 11.9 | 13.1 | 20.1 | 33.2 | 21.3 | 22.6 | 22.3 | 15.3 | 20.9 | — | — | — | |
| C-CONetModality=L2026.06 | 18.4 | 18.6 | 10 | 26.4 | 27.4 | 8.6 | 15.7 | 13.3 | 9.7 | 10.9 | 20.2 | 33 | 20.7 | 21.4 | 21.8 | 14.7 | 21.3 | — | — | — | |
| L-CONetModality=L2026.06 | 17.7 | 19.2 | 4 | 15.1 | 26.9 | 6.2 | 3.8 | 6.8 | 6 | 14.1 | 13.1 | 39.7 | 19.1 | 24 | 23.9 | 25.1 | 35.7 | — | — | — | |
| L-OccGenModality=LiDAR, Multi-sweep point clouds=true2026.06 | 16.8 | 18.8 | 5.1 | 14.8 | 19.6 | 7 | 7.7 | 11.5 | 6.7 | 13.9 | 14.6 | 36.4 | 22.1 | 22.8 | 22.3 | 20.6 | 24.5 | 31.6 | — | — | |
| BEVFormerModality=C2026.06 | 16.7 | 14.2 | 6.5 | 23.4 | 28.2 | 8.6 | 10.7 | 6.4 | 4 | 11.2 | 17.7 | 37.2 | 18 | 22.8 | 22.1 | 13.8 | 22.2 | — | — | — | |
| Hi-SOPCategory=Discriminative, Input=Camera2025.10 | 16.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 24.5 | — | — | |
| L-CONetModality=LiDAR, Multi-sweep point clouds=true2026.06 | 15.9 | 18 | 3.9 | 14.2 | 18.7 | 8.3 | 6.3 | 11 | 5.8 | 14.1 | 14.3 | 35.3 | 20.2 | 21.5 | 20.9 | 19.2 | 23 | 30.1 | — | — | |
| L-CONetModality=LiDAR, #Params.=65.63M, Inference time=266.32ms2026.06 | 15.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 30.1 | — | — | |
| L-CONetCategory=Discriminative, Input=LiDAR2025.10 | 15.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 30.9 | — | — | |
| LMSCNetModality=L2026.06 | 14.9 | 13.1 | 4.5 | 14.7 | 22.1 | 12.6 | 4.2 | 7.2 | 7.1 | 12.2 | 11.5 | 26.3 | 14.3 | 21.1 | 15.2 | 18.5 | 34.2 | — | — | — | |
| OccGenCategory=Generative, Input=Camera2025.10 | 14.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 23.4 | — | — | |
| C-OccGen2026.07 | 14.5 | 15.5 | 9.1 | 15.3 | 19.2 | 7.3 | 11.3 | 11.8 | 8.9 | 5.9 | 13.7 | 34.8 | 22 | 21.8 | 19.5 | 6 | 9.9 | 23.4 | — | — | |
| HTCLCategory=Discriminative, Input=Camera2025.10 | 14.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 21.4 | — | — | |
| SparseOccCategory=Discriminative, Input=Camera2025.10 | 14.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 21.8 | — | — | |
| SparseOccModality=Camera, Multi-sweep point clouds=false2026.06 | 14.1 | 16.1 | 9.3 | 15.1 | 18.6 | 7.3 | 9.4 | 11.2 | 9.4 | 7.2 | 13 | 31.8 | 21.7 | 20.7 | 18.8 | 6.1 | 10.6 | 21.8 | — | — | |
| SparseOcc2026.07 | 14.1 | 16.1 | 9.3 | 15.1 | 18.6 | 7.3 | 9.4 | 11.2 | 9.4 | 7.2 | 13 | 31.8 | 21.7 | 20.7 | 18.8 | 6.1 | 10.6 | 21.8 | 4 | 455 | |
| SparseOcc++2026.07 | 14.1 | 14.5 | 8.1 | 14.7 | 18.1 | 7.6 | 9.4 | 11 | 7.1 | 6.6 | 13.3 | 32.9 | 21.4 | 21.4 | 19.5 | 8 | 12.6 | 24.1 | 19.7 | 183 | |
| C-CONetModality=Camera, Multi-sweep point clouds=false2026.06 | 13.6 | 13.6 | 8.4 | 14.7 | 18.3 | 7.1 | 11 | 11.8 | 8.8 | 5.2 | 13 | 32.7 | 21.1 | 20.1 | 17.6 | 5.1 | 8.4 | 21.6 | — | — | |
| C-CONetModality=Camera, #Params.=117.99M, Inference time=394.77ms2026.06 | 13.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 21.6 | — | — | |
| C-CONetCategory=Discriminative, Input=Camera2025.10 | 12.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 20.1 | — | — | |
| C-CONet2026.07 | 12.8 | 13.2 | 8.1 | 15.4 | 17.2 | 6.3 | 11.2 | 10 | 8.3 | 4.7 | 12.1 | 31.4 | 18.8 | 18.7 | 16.3 | 4.8 | 8.2 | 20.1 | 0.7 | 1,810 | |
| JS3C-NetModality=LiDAR, Multi-sweep point clouds=true2026.06 | 12.7 | 14.5 | 4.4 | 13.5 | 12 | 7.8 | 4.4 | 7.3 | 6.9 | 9.2 | 9.2 | 27.4 | 15.8 | 15.9 | 16.4 | 14 | 24.8 | 29.6 | — | — | |
| JS3C-NetCategory=Discriminative, Input=LiDAR2025.10 | 12.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 30.2 | — | — | |
| OccSceneCategory=Generative, Input=Camera2025.10 | 12.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| L-OpenOccModality=LiDAR, Multi-sweep point clouds=true2026.06 | 11.9 | 11.1 | 4 | 11.4 | 12.9 | 7.2 | 6.2 | 10.1 | 4.4 | 8.1 | 11 | 23.3 | 15.8 | 15.5 | 15.6 | 15 | 18.7 | 22.3 | — | — | |
| L-OpenOccModality=LiDAR, #Params.=65.62M, Inference time=229.98ms2026.06 | 11.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 22.3 | — | — | |
| LMSCNetModality=LiDAR, Multi-sweep point clouds=true2026.06 | 11.8 | 12.9 | 5.2 | 12.8 | 12.6 | 6.6 | 4.9 | 6.3 | 6.5 | 8.8 | 7.7 | 24.3 | 12.7 | 16.5 | 14.5 | 14.2 | 22.1 | 26.7 | — | — | |
| LMSCNetCategory=Discriminative, Input=LiDAR2025.10 | 11.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 27.3 | — | — | |
| 3DSketchModality=Camera & Depth, Multi-sweep point clouds=false2026.06 | 11 | 12.3 | 5.2 | 10.3 | 12.1 | 7.1 | 4.9 | 5.5 | 6.9 | 8.4 | 7.4 | 21.9 | 15.4 | 13.6 | 12.1 | 12.1 | 21.2 | 25.3 | — | — | |
| C-OpenOccModality=Camera, Multi-sweep point clouds=false2026.06 | 10.9 | 9.3 | 7.2 | 11 | 12.5 | 7 | 9.3 | 8.9 | 5.2 | 4.9 | 10.2 | 23.1 | 17.4 | 15.4 | 14.3 | 8.4 | 11 | 17.9 | — | — | |
| AICNetModality=Camera & Depth, Multi-sweep point clouds=false2026.06 | 10.9 | 11.8 | 4.5 | 12.1 | 12.7 | 6 | 3.9 | 6.4 | 6.3 | 8.4 | 7.8 | 24.2 | 13.4 | 13 | 11.9 | 11.5 | 20.5 | 23.2 | — | — | |
| C-OpenOccModality=Camera, #Params.=99.20M, Inference time=274.09ms2026.06 | 10.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 17.9 | — | — | |
| 3DSketchCategory=Discriminative, Input=Camera&Depth2025.10 | 10.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 25.6 | — | — | |
| AICNetCategory=Discriminative, Input=Camera&Depth2025.10 | 10.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 23.8 | — | — | |
| OpenOccupancy2026.07 | 10.3 | 9.9 | 6.8 | 11.2 | 11.5 | 6.3 | 8.4 | 8.6 | 4.3 | 4.2 | 9.9 | 22 | 15.8 | 14.1 | 13.5 | 7.3 | 10.2 | 19.3 | 1.4 | 1,716 | |
| TPVFormerModality=Camera, Multi-sweep point clouds=false2026.06 | 8.3 | 9.7 | 4.5 | 11.5 | 10.7 | 5.5 | 4.6 | 6.3 | 5.4 | 6.9 | 6.9 | 14.1 | 9.8 | 8.9 | 9 | 9.9 | 8.5 | 15.1 | — | — | |
| TPVFormerCategory=Discriminative, Input=Camera2025.10 | 7.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 15.3 | — | — | |
| TPVFormer2026.07 | 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 | 15.3 | 2.3 | 1,132 | |
| MonoSceneModality=C2026.06 | 7.3 | 4 | 0.4 | 8 | 8 | 2.9 | 0.3 | 1.2 | 0.7 | 4 | 4.4 | 27.7 | 5.2 | 15.1 | 11.3 | 9 | 14.9 | — | — | — | |
| MonoSceneModality=Camera, Multi-sweep point clouds=false2026.06 | 7.2 | 7.3 | 4.3 | 9.6 | 7.1 | 6.2 | 3.5 | 5.9 | 4.7 | 5.6 | 4.9 | 15.6 | 6.8 | 7.9 | 7.6 | 10.5 | 7.9 | 17.1 | — | — | |
| MonoSceneCategory=Discriminative, Input=Camera2025.10 | 6.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 18.4 | — | — | |
| MonoScene2026.07 | 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 | 18.4 | — | — |