3D Object Detection On Kitti Cyclists Hard
Metrics
AP
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | AP |
|---|---|
| svga-net-sparse-voxel-graph-attention-network | 57.64% |
| voxelnet-end-to-end-learning-for-point-cloud | 44.37% |
| std-sparse-to-dense-3d-object-detector-for | 55.77% |
| pv-rcnn-point-voxel-feature-set-abstraction | 57.65% |
| pointrcnn-3d-object-proposal-generation-and | 53.59% |
| self-attention-based-context-aware-3d-object | 61.33% |
| joint-3d-proposal-generation-and-object | 46.61% |
| ipod-intensive-point-based-object-detector | 48.34% |
| frustum-pointnets-for-3d-object-detection | 50.39% |
| pointpillars-fast-encoders-for-object | 52.92% |
| frustum-convnet-sliding-frustums-to-aggregate | 57.03% |
| m3detr-multi-representation-multi-scale | 59.03% |