Semantic Occupancy Prediction on SemanticKITTI (test)
61.4mIoUDRVR
Evaluation results
| Method | Links | |||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DRVRModality=LiDAR2026.06 | 61.4 | 71.4 | 46.9 | 44.3 | 15.8 | 43.9 | 39.6 | 8.7 | 16.1 | 13.1 | 13.4 | 47.6 | 32.9 | 44.9 | 5.5 | 4.5 | 1.5 | 36.1 | 30.2 | 24.3 | — | — | — | |
| GaussianSSC2026.03 | 61.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 72.5 | 79.8 | — | |
| VPNetModality=LiDAR2026.06 | 60.4 | 72.4 | 44.3 | 40.5 | 14.8 | 44 | 37.2 | 4.3 | 14 | 9.8 | 8.2 | 45.3 | 30.9 | 42.1 | 4.9 | 2 | 2.4 | 32.7 | 17.1 | 8.8 | — | — | — | |
| SSC-RSModality=LiDAR2026.06 | 59.7 | 73.1 | 44.4 | 38.6 | 17.4 | 44.6 | 36.4 | 5.3 | 10.1 | 5.1 | 11.2 | 44.1 | 26 | 41.9 | 4.7 | 2.4 | 0.9 | 30.8 | 15 | 7.2 | — | — | — | |
| ETFormer2026.03 | 59.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 71.5 | 77.8 | — | |
| UDNetModality=LiDAR2026.06 | 59.4 | 62 | 35.1 | 28.2 | 9.1 | 39.5 | 33.9 | 3.8 | 0.8 | 0.4 | 4.4 | 40.9 | 23.2 | 32.3 | 0.5 | 0.3 | 0.3 | 24.4 | 18.8 | 13.1 | — | — | — | |
| SSA-SCModality=LiDAR2026.06 | 58.8 | 72.2 | 43.7 | 37.4 | 10.9 | 43.6 | 36.5 | 5.7 | 13.9 | 4.6 | 7.4 | 43.5 | 25.6 | 41.8 | 4.4 | 2.6 | 0.7 | 30.7 | 14.5 | 6.9 | — | — | — | |
| Local-DIFsModality=LiDAR2026.06 | 57.7 | 67.9 | 42.9 | 40.1 | 11.4 | 40.4 | 34.8 | 4.4 | 3.6 | 2.4 | 4.8 | 42.2 | 26.5 | 39.1 | 2.5 | 1.1 | 0 | 29 | 21.3 | 17.5 | — | — | — | |
| LMSCNet-SSModality=LiDAR2026.06 | 56.7 | 64.8 | 34.7 | 29 | 4.6 | 38.1 | 30.9 | 1.5 | 0 | 0 | 0.8 | 41.3 | 19.9 | 32.1 | 0 | 0 | 0 | 21.3 | 15 | 0.8 | — | — | — | |
| JS3C-NetModality=LiDAR2026.06 | 56.6 | 64.7 | 39.9 | 34.9 | 14.1 | 39.4 | 33.3 | 7.2 | 14.4 | 8.8 | 12.7 | 43.1 | 19.6 | 40.5 | 8 | 5.1 | 0.4 | 30.4 | 18.9 | 15.9 | — | — | — | |
| VoxFormer2026.03 | 52 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 61.5 | 71.1 | — | |
| TDSModality=LiDAR2026.06 | 50.6 | 62.2 | 31.6 | 23.3 | 6.5 | 34.1 | 29.5 | 2.5 | 0 | 0 | 0.1 | 40.1 | 21.9 | 33.1 | 0 | 0 | 0 | 24.1 | 16.9 | 6.9 | — | — | — | |
| SSCNet-FullModality=LiDAR2026.06 | 50 | 51.2 | 30.8 | 27.1 | 6.4 | 34.5 | 24.3 | 1.2 | 0.5 | 0.8 | 4.3 | 35.3 | 18.2 | 29 | 0.3 | 0.3 | 0 | 19.9 | 13.1 | 6.7 | — | — | — | |
| ProOOD (+VoxDet)Base Method=VoxDet* [102], Evaluation Protocol=Single-Frame2026.04 | 46.75 | 66.2 | 36.4 | 34.9 | 11.4 | 27.7 | 27.6 | 4.3 | 4.1 | 5 | 7.2 | 28.4 | 12.9 | 32.2 | 2.5 | 2.8 | 0.4 | 21.3 | 9.6 | 9.5 | — | — | 6.34 | |
| VoxDet*Implementation=Reproduced using official code, Evaluation Protocol=Single-Frame2026.04 | 46.69 | 65.8 | 35.5 | 33.9 | 11.4 | 27.1 | 27.5 | 5.2 | 5.1 | 5.6 | 4.5 | 27.7 | 11.9 | 31.2 | 2.3 | 2.7 | 0.5 | 21.1 | 9.5 | 9.2 | — | — | 6.17 | |
| VisHall3DModality=Camera2026.06 | 46.5 | 64.6 | 34.1 | 32 | 12.5 | 26.9 | 26.7 | 7.5 | 2.9 | 3.3 | 6.2 | 27.3 | 12.5 | 28 | 2.3 | 5.1 | 1.9 | 19.5 | 9.2 | 9.2 | — | — | — | |
| CGFormerEvaluation Protocol=Single-Frame2026.04 | 44.41 | 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 | — | — | 5.36 | |
| CGFormerModality=Camera2026.06 | 44.4 | 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 | — | — | — | |
| HASSCEvaluation Protocol=Single-Frame2026.04 | 43.4 | 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 | — | — | 3.92 | |
| ProOOD (+SGN)Base Method=SGN [63], Evaluation Protocol=Single-Frame2026.04 | 43.14 | 57.1 | 28 | 28 | 7.1 | 23.8 | 24.7 | 4.2 | 1.3 | 0.9 | 2.4 | 25.2 | 11.4 | 24.8 | 2.1 | 2 | 0.3 | 16.2 | 8.1 | 8 | — | — | 4.35 | |
| VoxFormerModality=Camera2026.06 | 43 | 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 | — | — | — | |
| LinkOccModality=Camera2026.06 | 43 | 55 | 28.5 | 25.4 | 7.1 | 24.1 | 23.2 | 5.1 | 0.3 | 2 | 5 | 23.2 | 8.1 | 27 | 2.2 | 2 | 0 | 13.7 | 7.8 | 6 | — | — | — | |
| VoxFormerEvaluation Protocol=Single-Frame2026.04 | 42.95 | 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 | — | — | 3.29 | |
| SymphoniesModality=Camera2026.06 | 42.2 | 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 | — | — | — | |
| SymphoniesEvaluation Protocol=Single-Frame2026.04 | 42.19 | 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 | — | — | 5.41 | |
| SGNEvaluation Protocol=Single-Frame2026.04 | 41.88 | 57.8 | 29.2 | 27.7 | 5.2 | 23.9 | 24.9 | 2.7 | 0.4 | 0.3 | 4 | 24.2 | 10 | 25.8 | 1.1 | 2.5 | 0.3 | 14.2 | 7.4 | 4.4 | — | — | 3.48 | |
| ESSCNetModality=LiDAR2026.06 | 41.8 | 43.8 | 28.1 | 26.9 | 10.3 | 29.8 | 26.4 | 5 | 0.3 | 5.4 | 9.1 | 35.8 | 20.1 | 28.7 | 2.9 | 2.7 | 0.1 | 23.3 | 16.4 | 16.7 | — | — | — | |
| SAG-IRTModality=Camera2026.06 | 38.4 | 56.2 | 30.2 | 28.4 | 6.8 | 18.5 | 22.9 | 4.7 | 1.7 | 1.9 | 5.9 | 20.1 | 8.6 | 19.1 | 2.2 | 4.1 | 0.5 | 13.3 | 4.2 | 5.8 | — | — | — | |
| OccFormerEvaluation Protocol=Single-Frame2026.04 | 34.53 | 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 | — | — | 2.64 | |
| OccFormerModality=Camera2026.06 | 34.5 | 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 | — | — | — | |
| TPVFormerModality=Camera2026.06 | 34.3 | 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 | — | — | — | |
| TPVFormerEvaluation Protocol=Single-Frame2026.04 | 34.25 | 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 | — | — | 2.25 | |
| MonoSceneModality=Camera2026.06 | 34.2 | 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 | — | — | — | |
| MonoSceneEvaluation Protocol=Single-Frame2026.04 | 34.16 | 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 | — | — | 2.29 | |
| GaussianOcc3DInput Modality=C&L2026.01 | 25.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GaussianOcc3DModality=Camera & LiDAR2026.01 | 25.2 | 69.3 | 41.8 | 37.8 | 10.7 | 42.9 | 35.6 | 8.7 | 8.9 | 6.9 | 9.2 | 45.6 | 28.2 | 41.1 | 5.1 | 2.8 | 0.6 | 32.8 | 27.1 | 23.1 | — | — | — | |
| OccMamba-128Input Modality=C&L2024.08 | 24.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OccMambaInput Modality=C&L2026.01 | 24.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OccMambaModality=Camera & LiDAR2026.01 | 24.6 | 68.7 | 41 | 35.9 | 9.1 | 40.8 | 34.8 | 8.8 | 8.8 | 6.5 | 8.9 | 44.9 | 28.7 | 40.6 | 4.2 | 2.6 | 0.6 | 32 | 27 | 23.3 | — | — | — | |
| Co-OccInput Modality=C&L2024.08 | 24.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Co-OccInput Modality=C&L2026.01 | 24.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Co-OccModality=Camera & LiDAR2026.01 | 24.4 | 72 | 43.5 | 42.5 | 10.2 | 35.1 | 40 | 6.4 | 4.4 | 3.3 | 8.8 | 41.2 | 30.8 | 40.8 | 1.6 | 3.3 | 0.4 | 32.7 | 26.6 | 20.7 | — | — | — | |
| SSC-RSInput Modality=L2024.08 | 24.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SSC-RSInput Modality=L2026.01 | 24.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SSC-RSModality=LiDAR2026.01 | 24.2 | 73.1 | 44.4 | 38.6 | 17.4 | 44.6 | 36.4 | 5.3 | 10.1 | 5.1 | 11.2 | 44.1 | 26 | 41.9 | 4.7 | 2.4 | 0.9 | 30.8 | 15 | 7.2 | — | — | — | |
| JS3C-NetInput Modality=L2024.08 | 23.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| JS3C-NetInput Modality=L2026.01 | 23.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| JS3C-NetModality=LiDAR2026.01 | 23.8 | 64 | 39 | 34.2 | 14.7 | 39.4 | 33.2 | 7.2 | 14 | 8.1 | 12.2 | 43.5 | 19.3 | 39.8 | 7.9 | 5.2 | 0 | 30.1 | 17.9 | 15.1 | — | — | — | |
| M-CONetInput Modality=C&L2024.08 | 20.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| M-CONetInput Modality=C&L2026.01 | 20.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| M-CONetModality=Camera & LiDAR2026.01 | 20.4 | 60.6 | 36.1 | 29 | 13 | 38.4 | 33.8 | 4.7 | 3 | 2.2 | 5.9 | 41.5 | 20.5 | 35.1 | 0.8 | 2.3 | 0.6 | 26 | 18.7 | 15.7 | — | — | — | |
| LMSCNetInput Modality=L2024.08 | 17 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LMSCNetInput Modality=L2026.01 | 17 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LMSCNetModality=LiDAR2026.01 | 17 | 64 | 33.1 | 24.9 | 3.2 | 38.7 | 29.5 | 2.5 | 0 | 0 | 0.1 | 40.5 | 19 | 30.8 | 0 | 0 | 0 | 20.5 | 15.7 | 0.5 | — | — | — | |
| SHTOccEvaluation Protocol=Single-Frame2026.04 | 15.07 | 57.8 | 28.9 | 26.3 | 12 | 23.4 | 24.6 | 3.6 | 3.5 | 1.8 | 4.6 | 24.9 | 11 | 22.5 | 3.7 | 3.8 | 0.1 | 17.1 | 8.7 | 9.4 | — | — | 5.65 | |
| RenderOccInput Modality=C2024.08 | 12.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RenderOccInput Modality=C2026.01 | 12.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RenderOccModality=Camera2026.01 | 12.8 | 57.2 | 28.4 | 16.1 | 0.9 | 18.2 | 24.9 | 6 | 0.4 | 0.3 | 3.7 | 26.2 | 4.9 | 3.6 | 1.9 | 3.1 | 0 | 9.1 | 6.2 | 3.4 | — | — | — | |
| OccFormerInput Modality=C2024.08 | 12.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OccFormerInput Modality=C2026.01 | 12.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OccFormerModality=Camera2026.01 | 12.3 | 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 | — | — | — | |
| SurroundOccInput Modality=C2024.08 | 11.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SurroundOccInput Modality=C2026.01 | 11.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SurroundOccModality=Camera2026.01 | 11.9 | 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 | — | — | — | |
| MonoSceneInput Modality=C2024.08 | 11.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MonoSceneInput Modality=C2026.01 | 11.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MonoSceneModality=Camera2026.01 | 11.1 | 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 | — | — | — |