3D Object Detection On Kitti Cars Easy Val
Métriques
AP
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | AP | Paper Title | Repository |
|---|---|---|---|
| Voxel R-CNN | 89.41 | Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection | - |
| MV3D | 71.29 | Multi-View 3D Object Detection Network for Autonomous Driving | - |
| PGD | 24.35 | Probabilistic and Geometric Depth: Detecting Objects in Perspective | - |
| SVGA-Net | 90.59 | SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds | - |
| SA-SSD+EBM | 95.45 | Accurate 3D Object Detection using Energy-Based Models | - |
| F-PointNet [Qi:2018fd] | 83.26 | Frustum PointNets for 3D Object Detection from RGB-D Data | - |
| PVCNN | 84.02 | Point-Voxel CNN for Efficient 3D Deep Learning | - |
| PV-RCNN++ | 92.57 | PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection | - |
| MV3D (LiDAR) | 71.19 | Multi-View 3D Object Detection Network for Autonomous Driving | - |
| M3DeTR | 92.29 | M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers | - |
| PC-RGNN | 90.94 | PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection | - |
0 of 11 row(s) selected.