Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph. (arXiv:2208.03624v1 [cs.CV])

Two-stage detectors have gained much popularity in 3D object detection. Most
two-stage 3D detectors utilize grid points, voxel grids, or sampled keypoints
for RoI feature extraction in the second stage. Such methods, however, are
inefficient in handling unevenly distributed and sparse outdoor points. This
paper solves this problem in three aspects. 1) Dynamic Point Aggregation. We
propose the patch search to quickly search points in a local region for each 3D
proposal. The dynamic farthest voxel sampling is then applied …

3d arxiv cnn cv detection graph r-cnn semantic