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

12/31/2019
by   Shaoshuai Shi, et al.
0

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. It takes advantages of efficient learning and high-quality proposals of the 3D voxel CNN and the flexible receptive fields of the PointNet-based networks. Specifically, the proposed framework summarizes the 3D scene with a 3D voxel CNN into a small set of keypoints via a novel voxel set abstraction module to save follow-up computations and also to encode representative scene features. Given the high-quality 3D proposals generated by the voxel CNN, the RoI-grid pooling is proposed to abstract proposal-specific features from the keypoints to the RoI-grid points via keypoint set abstraction with multiple receptive fields. Compared with conventional pooling operations, the RoI-grid feature points encode much richer context information for accurately estimating object confidences and locations. Extensive experiments on both the KITTI dataset and the Waymo Open dataset show that our proposed PV-RCNN surpasses state-of-the-art 3D detection methods with remarkable margins by using only point clouds.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/31/2021

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...
research
04/02/2021

HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection

We address the problem of 3D object detection, that is, estimating 3D ob...
research
10/09/2022

CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds

We present a novel two-stage fully sparse convolutional 3D object detect...
research
09/06/2021

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

We present a flexible and high-performance framework, named Pyramid R-CN...
research
08/18/2022

GraVoS: Gradient based Voxel Selection for 3D Detection

3D object detection within large 3D scenes is challenging not only due t...
research
08/08/2019

Fast Point R-CNN

We present a unified, efficient and effective framework for point-cloud ...
research
07/26/2022

ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection

Existing approaches for unsupervised point cloud pre-training are constr...

Please sign up or login with your details

Forgot password? Click here to reset