PV-RCNN: The Top-Performing LiDAR-only Solutions for 3D Detection / 3D Tracking / Domain Adaptation of Waymo Open Dataset Challenges
This work addresses the problem of accurate 3D perception for autonomous driving systems, though it is incremental as it builds upon the existing PV-RCNN framework.
The authors tackled 3D object detection, tracking, and domain adaptation using LiDAR-only data, achieving first place among LiDAR-only methods and second place overall in the Waymo Open Dataset Challenges 2020.
In this technical report, we present the top-performing LiDAR-only solutions for 3D detection, 3D tracking and domain adaptation three tracks in Waymo Open Dataset Challenges 2020. Our solutions for the competition are built upon our recent proposed PV-RCNN 3D object detection framework. Several variants of our PV-RCNN are explored, including temporal information incorporation, dynamic voxelization, adaptive training sample selection, classification with RoI features, etc. A simple model ensemble strategy with non-maximum-suppression and box voting is adopted to generate the final results. By using only LiDAR point cloud data, our models finally achieve the 1st place among all LiDAR-only methods, and the 2nd place among all multi-modal methods, on the 3D Detection, 3D Tracking and Domain Adaptation three tracks of Waymo Open Dataset Challenges. Our solutions will be available at https://github.com/open-mmlab/OpenPCDet