4D Occupancy Forecasting on Occ3D-nuScenes
47.62Semantic mIoU (1s)I2-World
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| I2-WorldInput=Occ GT2025.11 | 47.62 | 38.58 | 32.98 | 39.73 | 54.29 | 49.43 | 45.69 | 49.8 | 37.04 | |
| UniSceneInput=Occ GT2025.11 | 35.37 | 29.59 | 25.08 | 31.76 | 38.34 | 32.7 | 29.09 | 34.84 | — | |
| DOMEInput=Occ GT2025.11 | 35.11 | 25.89 | 20.29 | 27.1 | 43.99 | 35.36 | 29.74 | 36.36 | 6.54 | |
| SparseWorld-TC-Large*Input=Camera2025.11 | 32.76 | 29.62 | 27.28 | 29.89 | 55.28 | 53.56 | 51.71 | 53.52 | 2.08 | |
| DFIT-OccWorldInput=Occ GT2025.11 | 31.68 | 21.29 | 15.19 | 22.71 | 40.28 | 31.24 | 25.29 | 32.27 | — | |
| SparseWorld-TC-Small*Input=Camera2025.11 | 30.09 | 27.61 | 25.43 | 27.71 | 52.66 | 51.2 | 49.31 | 51.05 | 5.63 | |
| RenderWorldInput=Occ GT2025.11 | 28.69 | 18.89 | 14.83 | 20.89 | 37.74 | 28.41 | 24.08 | 30.08 | — | |
| SparseWorld-TC-LargeInput=Camera, N=48002025.11 | 28.64 | 26.28 | 24.36 | 26.42 | 50.57 | 49.26 | 47.8 | 49.21 | 3.58 | |
| SparseWorld-TC-SmallInput=Camera, Backbone=ResNet-50, N=6002025.11 | 27.95 | 25.51 | 23.35 | 25.6 | 50.69 | 49.15 | 47.23 | 49.02 | 9.35 | |
| LiAuto-GeoXInput=Camera, reconstruction backbone=DINOv2-Small2026.06 | 26.75 | 24.47 | 22.58 | 24.63 | 49.09 | 47.81 | 46.12 | 47.67 | — | |
| COME-FInput=Camera2025.11 | 26.56 | 21.73 | 18.49 | 22.26 | 48.08 | 43.84 | 40.28 | 44.07 | — | |
| COMEInput=Camera2026.06 | 26.56 | 21.73 | 18.49 | 22.26 | 48.08 | 43.84 | 40.28 | 44.07 | — | |
| SparseWorld-TCInput=Camera, backbone=ResNet-342026.06 | 26.33 | 24 | 22.05 | 24.13 | 48.2 | 46.88 | 45.13 | 46.64 | — | |
| OccWorld-OInput=Occ GT2025.11 | 25.78 | 15.14 | 10.51 | 17.14 | 34.63 | 25.07 | 20.18 | 26.63 | 18 | |
| OccLLaMA-OInput=Occ GT2025.11 | 25.05 | 19.49 | 15.26 | 19.93 | 34.56 | 28.53 | 24.41 | 29.17 | — | |
| DTTInput=Camera2025.11 | 24.87 | 18.3 | 15.63 | 19.6 | 38.98 | 37.45 | 31.89 | 36.11 | — | |
| DTTInput=Camera2026.06 | 24.87 | 18.3 | 15.63 | 19.6 | 38.98 | 37.45 | 31.89 | 36.11 | — | |
| DOME-FInput=Camera2025.11 | 24.12 | 17.41 | 13.24 | 18.25 | 35.18 | 27.9 | 23.44 | 28.84 | — | |
| DOME-FInput=Camera2026.06 | 24.12 | 17.41 | 13.24 | 18.25 | 35.18 | 27.9 | 23.44 | 28.84 | — | |
| Occ-LLMInput=Occ GT2025.11 | 24.02 | 21.65 | 17.29 | 20.99 | 36.65 | 32.14 | 28.77 | 35.52 | — | |
| I2-World-STCInput=Camera2025.11 | 21.67 | 18.78 | 16.47 | 18.97 | 30.55 | 28.76 | 26.99 | 28.77 | 4.21 | |
| I²-World-STCInput=Camera2026.06 | 21.67 | 18.78 | 16.47 | 18.97 | 30.55 | 28.76 | 26.99 | 28.77 | — | |
| DOME-STCInput=Camera2025.11 | 17.79 | 14.23 | 11.58 | 14.53 | 26.39 | 23.2 | 20.42 | 23.33 | 2.75 | |
| DOME-STCInput=Camera2026.06 | 17.79 | 14.23 | 11.58 | 14.53 | 26.39 | 23.2 | 20.42 | 23.33 | — | |
| OccVARInput=Camera2025.11 | 17.17 | 10.38 | 7.82 | 11.79 | 27.6 | 25.14 | 20.33 | 24.35 | — | |
| OccTENS-FInput=Camera2026.06 | 17.17 | 10.38 | 7.82 | 11.79 | 27.6 | 25.14 | 20.33 | 24.35 | — | |
| SparseWorldInput=Camera2025.11 | 14.93 | 13.15 | 11.51 | 13.2 | 22.96 | 22.1 | 21.05 | 22.03 | 8 | |
| SparseWorldInput=Camera2026.06 | 14.93 | 13.15 | 11.51 | 13.2 | 22.96 | 22.1 | 21.05 | 22.03 | — | |
| DFIT-OccWorldInput=Camera2025.11 | 13.38 | 10.16 | 7.96 | 10.5 | 19.18 | 16.85 | 25.02 | 17.02 | — | |
| DFIT-OccWorldInput=Camera2026.06 | 13.38 | 10.16 | 7.96 | 10.5 | 19.18 | 16.85 | 25.02 | 17.02 | — | |
| PreWorldInput=Camera2025.11 | 12.27 | 9.24 | 7.15 | 9.55 | 23.62 | 21.62 | 19.63 | 21.62 | — | |
| PreWorldInput=Camera2026.06 | 12.27 | 9.24 | 7.15 | 9.55 | 23.62 | 21.62 | 19.63 | 21.62 | — | |
| OccWorld-DInput=Camera2025.11 | 11.55 | 8.1 | 6.22 | 8.62 | 18.9 | 16.26 | 14.43 | 16.53 | — | |
| Occ-LLMInput=Camera2025.11 | 11.28 | 10.21 | 9.13 | 10.21 | 27.11 | 24.07 | 20.19 | 23.79 | — | |
| Occ-LLMInput=Camera2026.06 | 11.28 | 10.21 | 9.13 | 10.21 | 27.11 | 24.07 | 20.19 | 23.79 | — | |
| OccLLaMAInput=Camera2025.11 | 10.34 | 8.66 | 6.98 | 8.66 | 25.81 | 23.19 | 19.97 | 22.99 | — | |
| RenderWorldInput=Camera2025.11 | 2.83 | 2.55 | 2.37 | 2.58 | 14.61 | 13.61 | 12.98 | 13.73 | — |