PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection. (arXiv:2102.00463v3 [cs.CV] UPDATED)

3D object detection is receiving increasing attention from both industry and
academia thanks to its wide applications in various fields. In this paper, we
propose Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D
object detection on point clouds. First, we propose a novel 3D detector,
PV-RCNN, which boosts the 3D detection performance by deeply integrating the
feature learning of both point-based set abstraction and voxel-based sparse
convolution through two novel steps, i.e., the voxel-to-keypoint scene encoding
and the keypoint-to-grid RoI …

abstraction arxiv detection feature representation set vector voxel