ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds

Georg Bökman, Fredrik Kahl, Axel Flinth; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 10976-10985

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.

Related Material

[pdf] [supp]
[bibtex]
@InProceedings{Bokman_2022_CVPR, author = {B\"okman, Georg and Kahl, Fredrik and Flinth, Axel}, title = {ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10976-10985} }