CMB-ML: A Cosmic Microwave Background Dataset for the Oldest Possible Computer Vision Task
Abstract
The Cosmic Microwave Background (CMB) radiation is a pillar of modern cosmology that gives rise to a better understanding of the fundamental parameters of the universe. While the astrophysics community has developed computational methods to extract this signal from data, these methods have limited scalability, and several groups have proposed the adoption of computer vision based models for CMB signal extraction. However, these diverse models are difficult to compare: the underlying datasets and evaluations are inconsistent and have not been made publicly available. We propose CMB-ML, a dataset and library that integrates dataset creation, model inference, and result evaluation into a pipeline to fill this gap and to make the problem accessible to researchers outside of cosmology. The library and links for data are available at github.com/CMB-ML/cmb-ml.
Cite
Text
Amato et al. "CMB-ML: A Cosmic Microwave Background Dataset for the Oldest Possible Computer Vision Task." International Conference on Computer Vision, 2025.Markdown
[Amato et al. "CMB-ML: A Cosmic Microwave Background Dataset for the Oldest Possible Computer Vision Task." International Conference on Computer Vision, 2025.](https://mlanthology.org/iccv/2025/amato2025iccv-cmbml/)BibTeX
@inproceedings{amato2025iccv-cmbml,
title = {{CMB-ML: A Cosmic Microwave Background Dataset for the Oldest Possible Computer Vision Task}},
author = {Amato, James and Xie, Yunan and Medina-Varela, Leonel and Aljerwi, Ammar and McCutcheon, Adam and Rippentrop, T. Seth and Gonzalez, Kristian and Delabrouille, Jacques and Ishak, Mustapha and Ruozzi, Nicholas},
booktitle = {International Conference on Computer Vision},
year = {2025},
pages = {9418-9430},
url = {https://mlanthology.org/iccv/2025/amato2025iccv-cmbml/}
}