Hybrid Neural Representations for Spherical Data

Hyomin Kim, Yunhui Jang, Jaeho Lee, Sungsoo Ahn
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23972-23985, 2024.

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 cosmic 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 multi-layer perceptron 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-kim24i, title = {Hybrid Neural Representations for Spherical Data}, author = {Kim, Hyomin and Jang, Yunhui and Lee, Jaeho and Ahn, Sungsoo}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {23972--23985}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/kim24i/kim24i.pdf}, url = {https://proceedings.mlr.press/v235/kim24i.html}, 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 cosmic 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 multi-layer perceptron 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.} }
Endnote
%0 Conference Paper %T Hybrid Neural Representations for Spherical Data %A Hyomin Kim %A Yunhui Jang %A Jaeho Lee %A Sungsoo Ahn %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-kim24i %I PMLR %P 23972--23985 %U https://proceedings.mlr.press/v235/kim24i.html %V 235 %X 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 cosmic 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 multi-layer perceptron 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.
APA
Kim, H., Jang, Y., Lee, J. & Ahn, S.. (2024). Hybrid Neural Representations for Spherical Data. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:23972-23985 Available from https://proceedings.mlr.press/v235/kim24i.html.

Related Material