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

Published in CVPR, 2022

Yang You, Zelin Ye, Yujing Lou, Chengkun Li, Yong-Lu Li, Lizhuang Ma, Weiming Wang, Cewu Lu

arXiv / PDF / code / project page / BibTeX

Abstract

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, a 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 challenging large-scale datasets of real point cloud scans: ScanNet, SceneNN with 9.8 and 5.1 mAP improvement respectively.

BibTeX

@inproceedings{you2022canonical,
  title     = {Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes},
  author    = {Yang You and Zelin Ye and Yujing Lou and Chengkun Li and Yong-Lu Li and Lizhuang Ma and Weiming Wang and Cewu Lu},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2022},
  eprint    = {2011.12001},
  archivePrefix = {arXiv}
}

Recommended citation: You, Y., Ye, Z., Lou, Y., Li, C., Li, Y. L., Ma, L., Wang, W., & Lu, C. (2022). Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1193–1202).