3D Object Detection on KITTI (test) (Class-wise 3D vs BEV Summary)
77.88Car 3D AccuracyFore-Mamba3D
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Fore-Mamba3DAverage Recall=40, Difficulty Level=moderate2026.02 | 77.88 | 88.06 | 45.6 | 50.68 | 63.97 | 68.02 | |
| SeSameAverage Recall=40, Difficulty Level=moderate2026.02 | 76.83 | 87.49 | 35.34 | 41.22 | 54.46 | 61.7 | |
| TANetAverage Recall=40, Difficulty Level=moderate2026.02 | 75.94 | 86.54 | 44.34 | 51.38 | 59.44 | 63.77 | |
| PointRCNNAverage Recall=40, Difficulty Level=moderate2026.02 | 75.64 | 87.39 | 39.37 | 46.13 | 58.82 | 67.24 | |
| PointPillarsAverage Recall=40, Difficulty Level=moderate2026.02 | 74.99 | 86.1 | 43.53 | 50.23 | 59.07 | 62.25 | |
| SECONDAverage Recall=40, Difficulty Level=moderate2026.02 | 73.66 | — | 42.56 | — | 53.85 | — | |
| VoxelNetAverage Recall=40, Difficulty Level=moderate2026.02 | 65.11 | 79.26 | 33.69 | 40.74 | 48.36 | 54.76 |