SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds

7 Jun 2020  ·  Qingdong He, Zhengning Wang, Hao Zeng, Yi Zeng, Shuaicheng Liu, Bing Zeng ·

Accurate 3D object detection from point clouds has become a crucial component in autonomous driving. However, the volumetric representations and the projection methods in previous works fail to establish the relationships between the local point sets... In this paper, we propose Sparse Voxel-Graph Attention Network (SVGA-Net), a novel end-to-end trainable network which mainly contains voxel-graph module and sparse-to-dense regression module to achieve comparable 3D detection tasks from raw LIDAR data. Specifically, SVGA-Net constructs the local complete graph within each divided 3D spherical voxel and global KNN graph through all voxels. The local and global graphs serve as the attention mechanism to enhance the extracted features. In addition, the novel sparse-to-dense regression module enhances the 3D box estimation accuracy through feature maps aggregation at different levels. Experiments on KITTI detection benchmark demonstrate the efficiency of extending the graph representation to 3D object detection and the proposed SVGA-Net can achieve decent detection accuracy. read more

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Object Detection KITTI Cars Easy SVGA-Net AP 91.67% # 1
3D Object Detection KITTI Cars Easy val SVGA-Net AP 90.59 # 4
3D Object Detection KITTI Cars Hard SVGA-Net AP 74.63% # 6
3D Object Detection KITTI Cars Hard val SVGA-Net AP 79.15 # 4
3D Object Detection KITTI Cars Moderate SVGA-Net AP 82.95% # 2
3D Object Detection KITTI Cars Moderate val SVGA-Net AP 80.23 # 6
3D Object Detection KITTI Cyclists Easy SVGA-Net AP 79.22% # 2
3D Object Detection KITTI Cyclists Hard SVGA-Net AP 57.64% # 2
3D Object Detection KITTI Cyclists Moderate SVGA-Net AP 66.13% # 1
3D Object Detection KITTI Pedestrians Easy SVGA-Net AP 55.21% # 2
3D Object Detection KITTI Pedestrians Hard SVGA-Net AP 44.56% # 1
3D Object Detection KITTI Pedestrians Moderate SVGA-Net AP 47.71% # 1

Methods


No methods listed for this paper. Add relevant methods here