3D Object Detection On Kitti Cars Hard
평가 지표
AP
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | AP |
|---|---|
| accurate-3d-object-detection-using-energy | 72.78% |
| joint-3d-instance-segmentation-and-object | 74.30% |
| frustum-convnet-sliding-frustums-to-aggregate | 68.08% |
| 3d-dual-fusion-dual-domain-dual-query-camera-1 | 79.39% |
| pc-rgnn-point-cloud-completion-and-graph | 75.54% |
| svga-net-sparse-voxel-graph-attention-network | 74.63% |
| voxelnet-end-to-end-learning-for-point-cloud | 57.73% |
| 모델 8 | 80.38 % |
| pv-rcnn-point-voxel-feature-set-abstraction-1 | 77.15% |
| multi-task-multi-sensor-fusion-for-3d-object-1 | 68.41% |
| a-general-pipeline-for-3d-detection-of | 64.83% |
| glenet-boosting-3d-object-detectors-with | 78.43% |
| m3detr-multi-representation-multi-scale | 76.96% |
| voxel-r-cnn-towards-high-performance-voxel | 77.06 |
| probabilistic-and-geometric-depth-detecting | 9.39% |
| joint-3d-proposal-generation-and-object | 66.38% |
| ipod-intensive-point-based-object-detector | 66.33% |
| frustum-pointnets-for-3d-object-detection | 62.19% |
| pv-rcnn-point-voxel-feature-set-abstraction | 76.82% |
| std-sparse-to-dense-3d-object-detector-for | 76.06% |
| roarnet-a-robust-3d-object-detection-based-on | 59.16% |
| pointrgcn-graph-convolution-networks-for-3d | 70.60% |
| pointrcnn-3d-object-proposal-generation-and | 67.86% |
| se-ssd-self-ensembling-single-stage-object | 77.15% |
| cia-ssd-confident-iou-aware-single-stage | 72.87 |