3D Semantic Occupancy Prediction on Occ3D-nuScenes (val)
42.2Overall mIoUFDR-Occ
Evaluation results
| Method | Links | |||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| FDR-OccBackbone=ResNet-50, Size=256 × 704, Temporal Setting=+1f2026.07 | 42.2 | 72.1 | 14.2 | 48.7 | 28.8 | 44.8 | 53.8 | 26.8 | 29.9 | 30.3 | 33 | 35.4 | 41.3 | 82.6 | 45.2 | 54.2 | 57.3 | 49.2 | 42.2 | |
| DHD-MBackbone=ResNet-50, Size=256 × 704, Temporal Setting=+1f2026.07 | 41.5 | — | 12.7 | 48.7 | 26.3 | 43.2 | 52.9 | 27.3 | 28.5 | 28.5 | 30 | 35.8 | 40.2 | 83.1 | 44.7 | 54.7 | 57.7 | 48.9 | 42.1 | |
| COTRBackbone=ResNet-50, Size=256 × 704, Temporal Setting=+1f2026.07 | 41.4 | — | 12.2 | 48.5 | 29.1 | 44.7 | 53.3 | 27 | 29.2 | 28.9 | 31 | 35 | 39.5 | 81.8 | 42.5 | 53.7 | 56.9 | 48.2 | 42.1 | |
| FDR-OccBackbone=ResNet-50, Size=256 × 704, Temporal Setting=single-frame2026.07 | 41.2 | 71 | 13.6 | 46.5 | 28.3 | 43.4 | 53 | 26.8 | 29.1 | 29.6 | 31.6 | 36.4 | 39.9 | 81.6 | 44.3 | 53 | 55.5 | 47.2 | 40.6 | |
| CausalOccBackbone=ResNet-50, Size=256 × 704, Temporal Setting=single-frame2026.07 | 40.9 | 70.7 | 13.3 | 47.3 | 28.5 | 44 | 52.9 | 25.3 | 28.9 | 29.2 | 31.9 | 35.6 | 39.3 | 81.3 | 43.2 | 52.8 | 55.9 | 46.3 | 40.6 | |
| SA-OccBackbone=ResNet-50, Size=256 × 704, Temporal Setting=+1f2026.07 | 40.7 | — | 10.9 | 48.5 | 23.5 | 45.8 | 52.8 | 24.5 | 23.6 | 24.2 | 22.7 | 35 | 40.3 | 83.5 | 44.1 | 55.5 | 60 | 51.2 | 45.3 | |
| ALOccBackbone=ResNet-50, Size=256 × 704, Temporal Setting=single-frame2026.07 | 40.1 | 70.2 | 12.4 | 46.4 | 26.2 | 42.6 | 52.1 | 25.6 | 27.5 | 28.1 | 30.2 | 32.9 | 39.5 | 81.2 | 42.5 | 52.6 | 56 | 46.1 | 39.7 | |
| ProtoOccBackbone=ResNet-50, Size=256 × 704, Temporal Setting=single-frame2026.07 | 39.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| COTRBackbone=ResNet-50, Size=256 × 704, Temporal Setting=single-frame2026.07 | 39.1 | 69.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LightOcc-SBackbone=ResNet-50, Size=256 × 704, Temporal Setting=single-frame2026.07 | 37.9 | — | 11.7 | 45.6 | 25.4 | 43.1 | 48.7 | 21.4 | 25.6 | 26.6 | 29.2 | 33.2 | 35.1 | 80 | 41.8 | 50.4 | 53.9 | 39.4 | 34 | |
| BEVDetOccBackbone=ResNet-50, Size=256 × 704, Temporal Setting=single-frame2026.07 | 37.1 | 70.4 | 9.2 | 45.6 | 15.9 | 42.1 | 50 | 23 | 21 | 21.9 | 22.7 | 31.1 | 36.8 | 80.2 | 38.7 | 51.6 | 55.2 | 45.4 | 40.2 | |
| DHD-SBackbone=ResNet-50, Size=256 × 704, Temporal Setting=single-frame2026.07 | 36.5 | — | 10.6 | 43.2 | 23 | 40.6 | 47.3 | 21.7 | 23.3 | 23.9 | 23.4 | 31.8 | 34.2 | 80.2 | 41.3 | 50 | 54.1 | 38.7 | 33.5 | |
| FB-OccBackbone=ResNet-50, Size=256 × 704, Temporal Setting=single-frame2026.07 | 35.7 | 66.5 | 11.2 | 40 | 23.2 | 43.1 | 46.6 | 21.8 | 23.3 | 25.9 | 23.5 | 29.5 | 33.7 | 77.6 | 39 | 47.3 | 51 | 37.5 | 33 |