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.
@article{arxiv.2111.15341,
title = {ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds},
author = {Georg Bökman and Fredrik Kahl and Axel Flinth},
journal= {arXiv preprint arXiv:2111.15341},
year = {2022}
}