PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection

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 the Point-Voxel Region based Convolution Neural Networks (PV-RCNNs) for accurate 3D detection from point clouds... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Object Detection KITTI Cars Easy PV-RCNN++ AP 90.14% # 5
3D Object Detection KITTI Cars Easy val PV-RCNN++ AP 92.57 # 2
3D Object Detection KITTI Cars Hard PV-RCNN++ AP 77.15% # 1
3D Object Detection KITTI Cars Hard val PV-RCNN++ AP 82.69 # 1
3D Object Detection KITTI Cars Moderate PV-RCNN++ AP 81.88% # 3
3D Object Detection KITTI Cars Moderate val PV-RCNN++ AP 84.83 # 2

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions