← Search

Thomas Mitchel

2 accepted papers

2024

Neural Isometries: Taming Transformations for Equivariant ML

NeurIPS 2024poster

Real-world geometry and 3D vision tasks are replete with challenging symmetries that defy tractable analytical expression. In this paper, we introduce Neural Isometries, an autoencoder framework which learns to map the observation space to a general-purpose latent space wherein encodings are related…