Spin Spherical Fourier Neural Operators: Efficient Equivariant Learning for Vector and Spin Fields on the Sphere
cs.CV, astro-ph.IM, cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Comments: 27 pages, 15 figures
Code: https://github.com/astro-informatics/s2ai
License: http://creativecommons.org/licenses/by/4.0/
The gist: Many fields of physical interest on the sphere, such as wind, the polarisation of the cosmic microwave background and the shear of weak gravitational lensing, are spin fields…
Terminology
Abstract
Many fields of physical interest on the sphere, such as wind, the polarisation of the cosmic microwave background and the shear of weak gravitational lensing, are spin fields, whose values change phase when the local frame rotates. We extend spherical Fourier neural operators (SFNOs) to fields of any spin, through lifted spherical convolutions that are exactly rotationally equivariant. Lifting spin fields to Mackey functions on the rotation group provides the conceptual framework, while computation is performed exactly and efficiently through their harmonic representation and by appealing to sampling theorems on the sphere and rotation group. We construct spin SFNOs (S squared FNOs) from these building blocks. We demonstrate empirically that rotational equivariance holds to machine precision for these layers. We achieve state-of-the-art performance on existing benchmarks, and introduce new benchmarks on which spin-aware models outperform their scalar counterparts.
Sources
- Weak Gravitational Flexion
- SO(3)-Equivariant Neural Networks for Learning from Scalar and Vector Fields on Spheres
- Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast
- Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere
- FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale
- Weak lensing analysis in three dimensions
- Efficient Generalized Spherical CNNs
- Spherical CNNs
- A General Theory of Equivariant CNNs on Homogeneous Spaces
- Learning SO(3) Equivariant Representations with Spherical CNNs
- Spin-Weighted Spherical CNNs
- Scaling Spherical CNNs
- On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
- Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
- Neural Operator: Learning Maps Between Function Spaces
- GraphCast: Learning skillful medium-range global weather forecasting
- Euclid Definition Study Report
- Fourier Neural Operator for Parametric Partial Differential Equations
- Spin-Weighted Spherical Harmonics Enable Complete and Scalable $\mathrm{E}(3)$-Equivariant Networks
- Neural Operators with Localized Integral and Differential Kernels
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs