3D Object Detection On Kitti Cyclists
Métriques
AP
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | AP |
|---|---|
| eloss-in-the-way-a-sensitive-input-quality | 58% |
| frustum-convnet-sliding-frustums-to-aggregate | 64.68% |
| joint-3d-proposal-generation-and-object | 52.18% |
| pointpillars-fast-encoders-for-object | 59.07% |
| pointrcnn-3d-object-proposal-generation-and | 59.60% |
| 3d-fct-simultaneous-3d-object-detection-and | 75.86% |
| svga-net-sparse-voxel-graph-attention-network | 66.13% |
| voxelnet-end-to-end-learning-for-point-cloud | 48.36% |
| pv-rcnn-point-voxel-feature-set-abstraction | 63.71% |
| m3detr-multi-representation-multi-scale | 66.74% |
| frustum-pointnets-for-3d-object-detection | 56.77% |
| ipod-intensive-point-based-object-detector | 53.46% |
| std-sparse-to-dense-3d-object-detector-for | 62.53% |