On Invariance, Equivariance, Correlation and Convolution of Spherical Harmonic Representations for Scalar and Vectorial Data

Janis Keuper
7/6/2023
cs.LGcs.AI

No confident code implementation found for this paper.

Abstract

The mathematical representations of data in the Spherical Harmonic (SH) domain has recently regained increasing interest in the machine learning community. This technical report gives an in-depth introduction to the theoretical foundation and practical implementation of SH representations, summarizing works on rotation invariant and equivariant features, as well as convolutions and exact correlations of signals on spheres. In extension, these methods are then generalized from scalar SH representations to Vectorial Harmonics (VH), providing the same capabilities for 3d vector fields on spheres

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Spherical CNNs

81% match1 repo9722018

DeepSphere: towards an equivariant graph-based spherical CNN

79% match1 repo142019

Flexible Moment-Invariant Bases from Irreducible Tensors

79% match1 repo22025

Rotational Equivariance in Machine Learning: A Comprehensive Tutorial

78% match2026

Representing spherical tensors with scalar-based machine-learning models

77% match2025

Statistical-Computational Trade-offs in Learning Multi-Index Models via Harmonic Analysis

77% match2026

Cite this paper

@article{keuper2023invariance,
  title  = {On Invariance, Equivariance, Correlation and Convolution of Spherical Harmonic Representations for Scalar and Vectorial Data},
  author = {Janis Keuper},
  year   = {2023},
  eprint = {2307.03311},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.03311v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.03311.svg)](https://codeofpaper.com/paper/2307.03311)

Discussion