Accurate multi-slice reconstruction from limited measurement data is crucial to speed up the acquisition process in medical and scientific imaging. However, it remains challenging due to the ill-posed nature of the problem and the high computational and memory demands. We propose a framework that addresses these challenges by integrating partitioned diffusion priors with physics-based constraints. By doing so, we substantially reduce memory usage per GPU while preserving high reconstruction quality, outperforming both physics-only and full multi-slice reconstruction baselines for different modalities, namely Magnetic Resonance Imaging (MRI) and four-dimensional Scanning Transmission Electron Microscopy (4D-STEM). Additionally, we show that the proposed method improves in-distribution accuracy as well as strong generalization to out-of-distribution datasets.
@article{arxiv.2512.06977,
title = {Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging},
author = {Laurentius Valdy and Richard D. Paul and Alessio Quercia and Zhuo Cao and Xuan Zhao and Hanno Scharr and Arya Bangun},
journal= {arXiv preprint arXiv:2512.06977},
year = {2025}
}