ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds
Abstract
In this paper, we are concerned with rotation equivariance on 2D point cloud data. We describe a particular set of functions able to approximate any continuous rotation equivariant and permutation invariant function. Based on this result, we propose a novel neural network architecture for processing 2D point clouds and we prove its universality for approximating functions exhibiting these symmetries. We also show how to extend the architecture to accept a set of 2D-2D correspondences as indata, while maintaining similar equivariance properties. Experiments are presented on the estimation of essential matrices in stereo vision.
Cite
Text
Bökman et al. "ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds." Conference on Computer Vision and Pattern Recognition, 2022. doi:10.1109/CVPR52688.2022.01070Markdown
[Bökman et al. "ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds." Conference on Computer Vision and Pattern Recognition, 2022.](https://mlanthology.org/cvpr/2022/bokman2022cvpr-zznet/) doi:10.1109/CVPR52688.2022.01070BibTeX
@inproceedings{bokman2022cvpr-zznet,
title = {{ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds}},
author = {Bökman, Georg and Kahl, Fredrik and Flinth, Axel},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2022},
pages = {10976-10985},
doi = {10.1109/CVPR52688.2022.01070},
url = {https://mlanthology.org/cvpr/2022/bokman2022cvpr-zznet/}
}