Birds Eye View Object Detection On Kitti 1
Métriques
AP
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | AP |
|---|---|
| pointpillars-fast-encoders-for-object | 50.23% |
| frustum-pointpillars-a-multi-stage-approach | 52.23 % |
| voxelnet-end-to-end-learning-for-point-cloud | 40.74% |
| frustum-pointnets-for-3d-object-detection | 50.22% |
| std-sparse-to-dense-3d-object-detector-for | 51.39% |
| joint-3d-proposal-generation-and-object | 51.05% |