3D-Rotation-Equivariant Quaternion Neural Networks

Wen Shen, Binbin Zhang, Shikun Huang, Zhihua Wei, Quanshi Zhang

ECCV 2020

doi:10.1007/978-3-030-58565-5_32 /eccv/2020/shen2020eccv-3drotationequivariant/

Abstract

This paper proposes a set of rules to revise various neural networks for 3D point cloud processing to rotation-equivariant quaternion neural networks (REQNNs). We find that when a neural network uses quaternion features, the network feature naturally has the rotation-equivariance property. Rotation equivariance means that applying a specific rotation transformation to the input point cloud is equivalent to applying the same rotation transformation to all intermediate-layer quaternion features. Besides, the REQNN also ensures that the intermediate-layer features are invariant to the permutation of input points. Compared with the original neural network, the REQNN exhibits higher rotation robustness.

PDF ECCV Semantic Scholar

Cite

Text

Shen et al. "3D-Rotation-Equivariant Quaternion Neural Networks." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58565-5_32

Markdown

[Shen et al. "3D-Rotation-Equivariant Quaternion Neural Networks." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/shen2020eccv-3drotationequivariant/) doi:10.1007/978-3-030-58565-5_32

BibTeX

@inproceedings{shen2020eccv-3drotationequivariant,
  title     = {{3D-Rotation-Equivariant Quaternion Neural Networks}},
  author    = {Shen, Wen and Zhang, Binbin and Huang, Shikun and Wei, Zhihua and Zhang, Quanshi},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58565-5_32},
  url       = {https://mlanthology.org/eccv/2020/shen2020eccv-3drotationequivariant/}
}