Fast, Expressive SE$(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space

1 code implementation • 4 Oct 2023 • Erik J Bekkers, Sharvaree Vadgama, Rob D Hesselink, Putri A van der Linden, David W Romero

The theory of homogeneous spaces tells us how to do group convolutions with feature maps over the homogeneous space of positions $\mathbb{R}^3$, position and orientations $\mathbb{R}^3 {\times} S^2$, and the group $SE(3)$ itself.

Computational Efficiency Position +1