1802.08219
arxiv.org · 6,843 words · saved by 1 readers
N/A
Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds Nathaniel Thomas∗ Tess Smidt∗ arXiv:1802.08219v3 [cs.LG] 18 May 2018 Stanford University University of California, Berkeley Stanford, California, USA…
saved by
related reading
- Naturally Occurring Equivariance in Neural Networksdistill.pub
- 10. Equivariant Neural Networks — deep learning for molecules & materialsdmol.pub
- Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
- Modeling Symmetries | Mark Neumannmarkneumann.xyz
- Verifying your browser | OpenReviewopenreview.net
- [1810.13128] The Effect of Learning Strategy versus Inherent Architecture Properties on the Ability of Convolutional Neural Networks to Develop Transformation Invariancearxiv.org
- Neural Networks, Manifolds, and Topology -- colah's blogcolah.github.io
- [2212.02493] Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fieldsarxiv.org
- Clifford-Steerable Convolutional Neural Networksarxiv.org
- [1411.5908] Understanding image representations by measuring their equivariance and equivalencearxiv.org
- PointNetstanford.edu
- [2503.09829] SE(3)-Equivariant Robot Learning and Control: A Tutorial Surveyarxiv.org