English

Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging

Image and Video Processing 2025-12-09 v1 Machine Learning

Abstract

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.

Keywords

Cite

@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}
}

Comments

8 pages, 5 figures, AAAI AI2ASE 2026

R2 v1 2026-07-01T08:13:54.329Z