3DSSD: Point-Based 3D Single Stage Object Detector

Zetong Yang, Yanan Sun, Shu Liu, Jiaya Jia
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Prevalence of voxel-based 3D single-stage detectors contrast with underexplored point-based methods. In this paper, we present a lightweight point-based 3D single stage object detector 3DSSD to achieve decent balance of accuracy and efficiency. In this paradigm, all upsampling layers and the refinement stage, which are indispensable in all existing point-based methods, are abandoned. We instead propose a fusion sampling strategy in downsampling process to make detection on less representative
more » ... ints feasible. A delicate box prediction network, including a candidate generation layer and an anchor-free regression head with a 3D center-ness assignment strategy, is developed to meet the demand of high accuracy and speed. Our 3DSSD paradigm is an elegant single-stage anchor-free one. We evaluate it on widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art voxelbased single-stage methods by a large margin, and even yields comparable performance with two-stage point-based methods, with amazing inference speed of 25+ FPS, 2⇥ faster than former state-of-the-art point-based methods.
doi:10.1109/cvpr42600.2020.01105 dblp:conf/cvpr/YangS0J20 fatcat:aofaer6njbdc7khlfgz53y6g5e