3D Object Detection On Kitti Cars Easy
Métriques
AP
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | AP |
|---|---|
| Modèle 1 | 91.90 % |
| accurate-3d-object-detection-using-energy | 91.05% |
| pv-rcnn-point-voxel-feature-set-abstraction-1 | 90.14% |
| roarnet-a-robust-3d-object-detection-based-on | 83.71% |
| pc-rgnn-point-cloud-completion-and-graph | 89.13% |
| std-sparse-to-dense-3d-object-detector-for | 86.61% |
| frustum-convnet-sliding-frustums-to-aggregate | 85.88% |
| probabilistic-and-geometric-depth-detecting | 19.05% |
| 3d-dual-fusion-dual-domain-dual-query-camera-1 | 91.01% |
| glenet-boosting-3d-object-detectors-with | 91.67% |
| joint-3d-proposal-generation-and-object | 81.94% |
| pointrcnn-3d-object-proposal-generation-and | 84.32% |
| svga-net-sparse-voxel-graph-attention-network | 87.33% |
| frustum-pointnets-for-3d-object-detection | 81.2% |
| pv-rcnn-point-voxel-feature-set-abstraction | 90.25% |
| se-ssd-self-ensembling-single-stage-object | 91.49% |
| a-general-pipeline-for-3d-detection-of | 84.33% |
| joint-3d-instance-segmentation-and-object | 87.74% |
| pointrgcn-graph-convolution-networks-for-3d | 85.97% |
| m3detr-multi-representation-multi-scale | 90.28% |
| cia-ssd-confident-iou-aware-single-stage | 89.59% |
| spg-unsupervised-domain-adaptation-for-3d | 90.5% |
| ipod-intensive-point-based-object-detector | 79.75% |
| pointpillars-fast-encoders-for-object | 79.05% |
| multi-task-multi-sensor-fusion-for-3d-object-1 | 86.81% |
| voxelnet-end-to-end-learning-for-point-cloud | 77.47% |