Hybrid Neural Representations for Spherical Data
This work addresses the challenge of capturing intricate details in spherical data for scientific applications like climate and cosmology, representing an incremental improvement over existing coordinate-based methods.
The paper tackles the problem of representing spherical data like weather and CMB signals by introducing HNeR-S, a hybrid neural representation that combines spherical feature-grids with MLPs, achieving effectiveness in tasks such as regression, super-resolution, temporal interpolation, and compression.
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.