We present an automatic diffusion-based method to estimate the mass density distribution in galaxy clusters, trained on our DarkClusters-15k dataset, the largest collection of 15,000 simulated galaxy clusters with paired mass and photometry maps.
Galaxy clusters are powerful probes of astrophysics and cosmology through gravitational lensing: the clusters' mass, dominated by 85% dark matter, distorts background light. Yet, mass reconstruction lacks the scalability and large-scale benchmarks to process the hundreds of thousands of clusters expected from forthcoming wide-field surveys.
We introduce a fully automated method to reconstruct cluster surface mass density from photometry and gravitational lensing observables. Central to our approach is DarkClusters-15k, our new dataset of 15,000 simulated clusters with paired mass and photometry maps, the largest benchmark to date, spanning multiple redshifts and simulation frameworks. We train a plug-and-play diffusion prior on DarkClusters-15k that learns the statistical relationship between mass and light, and draw posterior samples constrained by weak- and strong-lensing observables; this yields principled reconstructions driven by explicit physics, alongside well-calibrated uncertainties.
Our approach requires no expert tuning, runs in minutes rather than hours, achieves higher accuracy, and matches expertly-tuned reconstructions of the MACS 1206 cluster. We release our method and DarkClusters-15k to support development and benchmarking for upcoming wide-field cosmological surveys.
@inproceedings{royo2026mapping,
title={Mapping dark-matter clusters via physics-guided diffusion models},
author={Royo, Diego and Zhao, Brandon and Mu{\~n}oz, Adolfo and Gutierrez, Diego and Bouman, Katherine L},
booktitle={European Conference on Computer Vision},
pages={394--413},
year={2026},
organization={Springer}
}