3D Object Detection On Kitti Pedestrians
평가 지표
AP
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | AP |
|---|---|
| object-as-hotspots-an-anchor-free-3d-object | 44.81% |
| svga-net-sparse-voxel-graph-attention-network | 47.71% |
| ipod-intensive-point-based-object-detector | 44.68% |
| frustum-pointnets-for-3d-object-detection | 42.15% |
| 3d-fct-simultaneous-3d-object-detection-and | 58.4% |
| std-sparse-to-dense-3d-object-detector-for | 44.24% |
| m3detr-multi-representation-multi-scale | 41.02% |
| joint-3d-proposal-generation-and-object | 42.81% |
| voxelnet-end-to-end-learning-for-point-cloud | 33.69% |
| frustum-convnet-sliding-frustums-to-aggregate | 43.38% |
| frustum-pointpillars-a-multi-stage-approach | 42.89 % |
| pointpillars-fast-encoders-for-object | 41.92% |