A Density-Aware PointRCNN for 3D Object Detection in Point Clouds
This work addresses a domain-specific issue in autonomous driving by providing an incremental improvement to 3D object detection methods.
The paper tackles the problem of non-uniform point cloud density in 3D object detection by proposing an improved PointRCNN with a multi-branch backbone and uncertainty-based sampling, achieving about 0.8 AP higher performance than the baseline on the KITTI val set.
We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds. An uncertainty-based sampling policy is proposed to deal with the distribution differences of different point clouds. The new model can achieve about 0.8 AP higher performance than the baseline PointRCNN on KITTI val set. In addition, a simplified model using a single scale grouping for each set-abstraction layer can achieve competitive performance with less computational cost.