A Simple and Universal Rotation Equivariant Point-cloud Network
This work provides a more accessible solution for researchers and practitioners in 3D computer vision, though it is incremental as it builds on existing equivariant architectures.
The authors tackled the problem of designing a simpler yet equally universal rotation equivariant network for 3D point clouds, achieving competitive performance on ModelNet40.
Equivariance to permutations and rigid motions is an important inductive bias for various 3D learning problems. Recently it has been shown that the equivariant Tensor Field Network architecture is universal -- it can approximate any equivariant function. In this paper we suggest a much simpler architecture, prove that it enjoys the same universality guarantees and evaluate its performance on Modelnet40. The code to reproduce our experiments is available at \url{https://github.com/simpleinvariance/UniversalNetwork}