HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
arXiv:2003.00186
Abstract
We present Hybrid Voxel Network (HVNet), a novel one-stage unified network for point cloud based 3D object detection for autonomous driving. Recent studies show that 2D voxelization with per voxel PointNet style feature extractor leads to accurate and efficient detector for large 3D scenes. Since the size of the feature map determines the computation and memory cost, the size of the voxel becomes a parameter that is hard to balance. A smaller voxel size gives a better performance, especially for small objects, but a longer inference time. A larger voxel can cover the same area with a smaller feature map, but fails to capture intricate features and accurate location for smaller objects. We present a Hybrid Voxel network that solves this problem by fusing voxel feature encoder (VFE) of different scales at point-wise level and project into multiple pseudo-image feature maps. We further propose an attentive voxel feature encoding that outperforms plain VFE and a feature fusion pyramid network to aggregate multi-scale information at feature map level. Experiments on the KITTI benchmark show that a single HVNet achieves the best mAP among all existing methods with a real time inference speed of 31Hz.
arXiv commentaccepted to CVPR 2020
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Deep Continuous Fusion for Multi-Sensor 3D Object Detection
- FSSD: Feature Fusion Single Shot Multibox Detector
- HDNET: Exploiting HD Maps for 3D Object Detection
- Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
- IPOD: Intensive Point-based Object Detector for Point Cloud
- End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds
- Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds
- IoU Loss for 2D/3D Object Detection