3D Object Detection On Kitti Cyclists Easy
Metrics
AP
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | AP |
|---|---|
| frustum-pointnets-for-3d-object-detection | 71.96% |
| pointrcnn-3d-object-proposal-generation-and | 73.93% |
| voxelnet-end-to-end-learning-for-point-cloud | 61.22% |
| joint-3d-proposal-generation-and-object | 64.0% |
| m3detr-multi-representation-multi-scale | 83.83% |
| std-sparse-to-dense-3d-object-detector-for | 78.89% |
| frustum-convnet-sliding-frustums-to-aggregate | 79.58% |
| 3d-fct-simultaneous-3d-object-detection-and | 89.15% |
| ipod-intensive-point-based-object-detector | 71.40% |
| svga-net-sparse-voxel-graph-attention-network | 79.22% |
| pointpillars-fast-encoders-for-object | 75.78% |
| pv-rcnn-point-voxel-feature-set-abstraction | 78.60% |