PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection

Authors

  • Yanan Zhang Beihang University
  • Di Huang Beihang University
  • Yunhong Wang Beihang University

Keywords:

3D Computer Vision

Abstract

LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds caused by distant and occluded objects. In this paper, we propose a novel two-stage framework, namely PC-RGNN, which deals with these challenges by two specific solutions. On the one hand, we introduce a point cloud completion module to recover high-quality proposals of dense points and entire view with original structures preserved. On the other hand, a graph neural network module, is designed, which comprehensively captures relations among points by the local-global attention mechanism as well as the multi-scale graph based context aggregation and substantially strengthens encoded features. Extensive experiments on the KITTI benchmark show that the proposed approach outperforms the previous state-of-the-art baselines by remarkable margins, highlighting its effectiveness.

Downloads

Published

2021-05-18

How to Cite

Zhang, Y., Huang, D., & Wang, Y. (2021). PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 3430-3437. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16456

Issue

Section

AAAI Technical Track on Computer Vision III