3D Occupancy Prediction on SurroundOcc
30.4mIoUHiPR
Evaluation results
| Method | Links | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HiPRInput=C+L, Backbone=R502026.05 | 30.4 | 29.9 | 23.1 | 34.8 | 38.4 | 23.4 | 29.7 | 28.8 | 21.9 | 22.4 | 32 | 43.8 | 28.6 | 30.6 | 29.9 | 30.6 | 39.4 | — | |
| OccCylindricalInput=C+L, Backbone=R502026.05 | 28.7 | 26.2 | 22.1 | 31.5 | 36.8 | 18 | 27.8 | 29.9 | 23.9 | 20.6 | 28.3 | 43 | 23.1 | 28 | 27.8 | 30.8 | 41 | — | |
| HiPR-miniInput=C+L, Backbone=R502026.05 | 28.6 | 27.9 | 21.7 | 33.2 | 36.8 | 22.8 | 27.7 | 27 | 19.9 | 20.2 | 30 | 41.4 | 26.8 | 28.7 | 27.7 | 28.3 | 37.5 | — | |
| OccFusionInput=C+L+R, Backbone=R1012026.05 | 28.3 | 28.3 | 21 | 35.1 | 36.8 | 20.3 | 26.2 | 25.9 | 19.2 | 21.3 | 30.6 | 40.1 | 23.8 | 25.6 | 27.6 | 29.8 | 40.8 | — | |
| OccFusionInput=C+L, Backbone=R1012026.05 | 27.6 | 25.2 | 19.9 | 34.8 | 36.2 | 20 | 23.1 | 25.3 | 17.5 | 22.7 | 30.1 | 39.5 | 23.3 | 25.7 | 27.6 | 29.5 | 40.6 | — | |
| Co-OccInput=C+L, Backbone=R1012026.05 | 27.1 | 28.1 | 16.1 | 34 | 37.2 | 17 | 21.6 | 20.8 | 15.9 | 21.9 | 28.7 | 42.3 | 25.4 | 29.1 | 28.6 | 28.2 | 38 | — | |
| M-CONetInput=C+L, Backbone=R1012026.05 | 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 | — | |
| LightOccConfiguration=LightOcc-L, Backbone=Swin-Transformer-Base, Resolution=512x14082024.12 | 23.68 | 24.65 | 15.37 | 31.02 | 33.48 | 14.27 | 19.42 | 17.17 | 15.21 | 16.81 | 25.63 | 42.47 | 26.31 | 29.15 | 27.35 | 15.85 | 24.74 | 34.01 | |
| GaussianWorld2024.12 | 22.13 | 21.38 | 14.12 | 27.71 | 31.84 | 13.66 | 17.43 | 13.66 | 11.46 | 15.09 | 23.94 | 42.98 | 24.86 | 28.84 | 26.74 | 15.69 | 24.74 | 33.4 | |
| LowRankOcc2024.12 | 21.51 | 22.49 | 12.45 | 30.32 | 33.63 | 10.35 | 14.31 | 13.67 | 12.4 | 15.09 | 25.99 | 39.52 | 23.21 | 26.67 | 25.19 | 16.23 | 22.66 | 32.78 | |
| GaussianFormer-22024.12 | 20.82 | 21.39 | 13.44 | 28.49 | 30.82 | 10.92 | 15.84 | 13.55 | 10.53 | 14.04 | 22.92 | 40.61 | 24.36 | 26.08 | 24.27 | 13.83 | 21.98 | 31.74 | |
| GaussianFormer2Input=C, Backbone=R1012026.05 | 20.8 | 21.4 | 13.4 | 28.5 | 30.8 | 10.9 | 15.8 | 13.6 | 10.5 | 14 | 22.9 | 40.6 | 24.4 | 26.1 | 24.3 | 13.8 | 22 | — | |
| SurroundOccInput=C, Backbone=R1012026.05 | 20.3 | 20.6 | 11.7 | 28.1 | 30.9 | 10.7 | 15.1 | 14.1 | 12.1 | 14.4 | 22.3 | 37.3 | 23.7 | 24.5 | 22.8 | 14.9 | 21.9 | — | |
| SurroundOcc2024.12 | 20.3 | 20.59 | 11.68 | 28.06 | 30.86 | 10.7 | 15.14 | 14.09 | 12.06 | 14.38 | 22.26 | 37.29 | 23.7 | 24.49 | 22.77 | 14.89 | 21.86 | 31.49 | |
| GaussianFormer2024.12 | 19.1 | 19.52 | 11.26 | 26.11 | 29.78 | 10.47 | 13.83 | 12.58 | 8.67 | 12.74 | 21.57 | 39.63 | 23.28 | 24.46 | 22.99 | 9.59 | 19.12 | 29.83 | |
| OccFormer2024.12 | 19.03 | 18.65 | 10.41 | 23.92 | 30.29 | 10.31 | 14.19 | 13.59 | 10.13 | 12.49 | 20.77 | 38.78 | 19.79 | 24.19 | 22.21 | 13.48 | 21.35 | 31.39 | |
| GaussianFormerInput=C, Backbone=R1012026.05 | 17.3 | 19.5 | 11.3 | 26.1 | 29.8 | 10.5 | 13.8 | 12.6 | 8.7 | 12.7 | 21.6 | 39.6 | 23.3 | 24.5 | 23 | 9.6 | 19.1 | — | |
| TPVFormerInput=C, Backbone=R1012026.05 | 17.1 | 16 | 5.3 | 23.9 | 27.3 | 9.8 | 8.7 | 7.1 | 5.2 | 11 | 19.2 | 38.9 | 21.3 | 24.3 | 23.2 | 11.7 | 20.8 | — | |
| TPVFormer2024.12 | 17.1 | 15.96 | 5.31 | 23.86 | 27.32 | 9.79 | 8.74 | 7.09 | 5.2 | 10.97 | 19.22 | 38.87 | 21.25 | 24.26 | 23.15 | 11.73 | 20.81 | 30.86 | |
| BEVFormerInput=C, Backbone=R1012026.05 | 16.8 | 14.2 | 6.6 | 23.5 | 28.3 | 8.7 | 10.8 | 6.6 | 4.1 | 11.2 | 17.8 | 37.3 | 18 | 22.9 | 22.2 | 13.8 | 22.2 | — | |
| BEVFormer2024.12 | 16.75 | 14.22 | 6.58 | 23.46 | 28.28 | 8.66 | 10.77 | 6.64 | 4.05 | 11.2 | 17.78 | 37.28 | 18 | 22.88 | 22.17 | 13.8 | 22.21 | 30.5 | |
| Atlas2024.12 | 15 | 10.64 | 5.68 | 19.66 | 24.94 | 8.9 | 8.84 | 6.47 | 3.28 | 10.42 | 16.21 | 34.86 | 15.46 | 21.89 | 20.95 | 11.21 | 20.54 | 28.66 | |
| MonoScene2024.12 | 7.31 | 4.03 | 0.35 | 8 | 8.04 | 2.9 | 0.28 | 1.16 | 0.67 | 4.01 | 4.35 | 27.72 | 5.2 | 15.13 | 11.29 | 9.03 | 14.86 | 23.96 |