Azimuthal Rotational Equivariance in Spherical CNNs

1 Jan 2021  ·  Carl Toft, Georg Bökman, Fredrik Kahl ·

In this work, we analyze linear operators from $L^2(S^2) \rightarrow L^2(S^2)$ which are equivariant to azimuthal rotations, that is, rotations around the z-axis. Several high-performing neural networks defined on the sphere are indeed equivariant to azimuthal rotations, but not $SO(3)$. Our main result is to show that a linear operator acting on band-limited functions on the sphere is equivariant to azimuthal rotations if and only if it can be realized as a block-diagonal matrix acting on the spherical harmonic expansion coefficients of its input. Further, we show that such an operation can be interpreted as a convolution or equivalently a correlation. Our theoretical findings are backed up with experimental results demonstrating that a state-of-the-art pipeline can be improved by making it fully equivariant to azimuthal rotations.

PDF Abstract
No code implementations yet. Submit your code now

Tasks


Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods