GraVoS: Voxel Selection for 3D Point-Cloud Detection

arXiv:2208.08780v3 Announce Type: replace
Abstract: 3D object detection within large 3D scenes is challenging not only due to the sparsity and irregularity of 3D point clouds, but also due to both the extreme foreground-background scene imbalance and class imbalance. A common approach is to add ground-truth objects from other scenes. Differently, we propose to modify the scenes by removing elements (voxels), rather than adding ones. Our approach selects the "meaningful" voxels, in a manner that addresses both types of dataset …

3d object 3d object detection 3d scenes abstract arxiv class cloud cs.cv detection ground-truth object objects point-cloud sparsity truth type voxel