Hybrid Neural Representations for Spherical Data

TL;DR

This paper introduces Hybrid Neural Representations for Spherical data (HNeR-S), combining spherical feature-grids with neural networks to improve modeling of complex signals like weather and CMB data.

Contribution

It proposes a novel hybrid neural approach using spherical feature-grids and MLPs, tailored for detailed spherical data analysis, addressing limitations of previous coordinate-based methods.

Findings

Effective in regression, super-resolution, and interpolation tasks

Outperforms existing methods in capturing nonlinear spherical signals

Versatile across weather and cosmic microwave background data

Abstract

In this paper, we study hybrid neural representations for spherical data, a domain of increasing relevance in scientific research. In particular, our work focuses on weather and climate data as well as comic microwave background (CMB) data. Although previous studies have delved into coordinate-based neural representations for spherical signals, they often fail to capture the intricate details of highly nonlinear signals. To address this limitation, we introduce a novel approach named Hybrid Neural Representations for Spherical data (HNeR-S). Our main idea is to use spherical feature-grids to obtain positional features which are combined with a multilayer perception to predict the target signal. We consider feature-grids with equirectangular and hierarchical equal area isolatitude pixelization structures that align with weather data and CMB data, respectively. We extensively verify the effectiveness of our HNeR-S for regression, super-resolution, temporal interpolation, and compression tasks.