Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
Nathaniel Thomas, Tess Smidt, Steven Kearnes, Lusann Yang, Li Li, Kai Kohlhoff, Patrick Riley
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/tensorfieldnetworks/tensorfieldnetworksOfficialIn papertf★ 0
- github.com/e3nn/e3nnpytorch★ 1,227
- github.com/e3nn/e3nn-jaxjax★ 225
- github.com/mariogeiger/se3cnnpytorch★ 0
- github.com/luca310795/tensor-field-networkstf★ 0
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.