PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

CVPR 2020 Shaoshuai ShiChaoxu GuoLi JiangZhe WangJianping ShiXiaogang WangHongsheng Li

We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our proposed method deeply integrates both 3D voxel Convolutional Neural Network (CNN) and PointNet-based set abstraction to learn more discriminative point cloud features... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Birds Eye View Object Detection KITTI Cars Easy PV-RCNN AP 94.98 # 1
3D Object Detection KITTI Cars Easy PV-RCNN AP 90.25% # 2
Birds Eye View Object Detection KITTI Cars Hard PV-RCNN AP 86.14 # 2
3D Object Detection KITTI Cars Hard PV-RCNN AP 76.82% # 1
3D Object Detection KITTI Cars Moderate PV-RCNN AP 81.43% # 2
Birds Eye View Object Detection KITTI Cars Moderate PV-RCNN AP 90.65% # 1
3D Object Detection KITTI Cyclists Easy PV-RCNN AP 78.60% # 4
Birds Eye View Object Detection KITTI Cyclists Easy PV-RCNN AP 82.49 # 1
3D Object Detection KITTI Cyclists Hard PV-RCNN AP 57.65% # 1
Birds Eye View Object Detection KITTI Cyclists Hard PV-RCNN AP 62.41 # 1
Birds Eye View Object Detection KITTI Cyclists Moderate PV-RCNN AP 68.89% # 1
3D Object Detection KITTI Cyclists Moderate PV-RCNN AP 63.71% # 3
3D Object Detection waymo all_ns PV-RCNN APH/L2 71.52 # 1
3D Object Detection waymo cyclist PV-RCNN APH/L2 71.16 # 1
3D Object Detection waymo pedestrian PV-RCNN APH/L2 70.16 # 1
3D Object Detection waymo vehicle PV-RCNN APH/L2 73.23 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet