Tensor Field Networks Rotation And Translationequivariant Neural Networks For 3d Point Clouds

# Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds

**arXiv ID:** 1802.08219
**Authors:** Nathaniel Thomas, Tess Smidt, Steven Kearnes, Lusann Yang, Li Li, Kai Kohlhoff, Patrick Riley
**Published:** 2018-02-22T18:17:31Z
**Abstract:**
We introduce tensor field neural networks, which are locally equivariant to 3D rotations, translations, and permutations of points at every layer. 3D rotation equivariance removes the need for data augmentation to identify features in arbitrary orientations. Our network uses filters built from spherical harmonics; due to the mathematical consequences of this filter choice, each layer accepts as input (and guarantees as output) scalars, vectors, and higher-order tensors, in the geometric sense of these terms. We demonstrate the capabilities of tensor field networks with tasks in geometry, physics, and chemistry.

## Skill Description

This skill is generated from the arXiv paper: Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds (1802.08219).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:1802.08219](http://arxiv.org/abs/1802.08219v3)