LiDAR R-CNN: An Efficient and Universal 3D Object Detector
This work addresses the need for efficient and high-precision 3D detection in autonomous driving perception systems, offering a universal improvement over existing methods.
The paper tackles the problem of improving 3D object detection in LiDAR point clouds for autonomous driving by proposing LiDAR R-CNN, a second-stage detector that enhances existing detectors, achieving new state-of-the-art results on datasets like Waymo Open Dataset and KITTI with minor computational cost.
LiDAR-based 3D detection in point cloud is essential in the perception system of autonomous driving. In this paper, we present LiDAR R-CNN, a second stage detector that can generally improve any existing 3D detector. To fulfill the real-time and high precision requirement in practice, we resort to point-based approach other than the popular voxel-based approach. However, we find an overlooked issue in previous work: Naively applying point-based methods like PointNet could make the learned features ignore the size of proposals. To this end, we analyze this problem in detail and propose several methods to remedy it, which bring significant performance improvement. Comprehensive experimental results on real-world datasets like Waymo Open Dataset (WOD) and KITTI dataset with various popular detectors demonstrate the universality and superiority of our LiDAR R-CNN. In particular, based on one variant of PointPillars, our method could achieve new state-of-the-art results with minor cost. Codes will be released at https://github.com/tusimple/LiDAR_RCNN .