Back to Search Start Over

Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes

Authors :
You, Yang
Ye, Zelin
Lou, Yujing
Li, Chengkun
Li, Yong-Lu
Ma, Lizhuang
Wang, Weiming
Lu, Cewu
Publication Year :
2020

Abstract

3D object detection has attracted much attention thanks to the advances in sensors and deep learning methods for point clouds. Current state-of-the-art methods like VoteNet regress direct offset towards object centers and box orientations with an additional Multi-Layer-Perceptron network. Both their offset and orientation predictions are not accurate due to the fundamental difficulty in rotation classification. In the work, we disentangle the direct offset into Local Canonical Coordinates (LCC), box scales and box orientations. Only LCC and box scales are regressed, while box orientations are generated by a canonical voting scheme. Finally, an LCC-aware back-projection checking algorithm iteratively cuts out bounding boxes from the generated vote maps, with the elimination of false positives. Our model achieves state-of-the-art performance on three standard real-world benchmarks: ScanNet, SceneNN and SUN RGB-D. Our code is available on https://github.com/qq456cvb/CanonicalVoting.<br />Comment: Accepted to CVPR2022

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2011.12001
Document Type :
Working Paper