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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Valdy, Laurentius, Paul, Richard D., Quercia, Alessio, Cao, Zhuo, Zhao, Xuan, Scharr, Hanno, Bangun, Arya
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914185873457152
author Valdy, Laurentius
Paul, Richard D.
Quercia, Alessio
Cao, Zhuo
Zhao, Xuan
Scharr, Hanno
Bangun, Arya
author_facet Valdy, Laurentius
Paul, Richard D.
Quercia, Alessio
Cao, Zhuo
Zhao, Xuan
Scharr, Hanno
Bangun, Arya
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06977
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging
Valdy, Laurentius
Paul, Richard D.
Quercia, Alessio
Cao, Zhuo
Zhao, Xuan
Scharr, Hanno
Bangun, Arya
Image and Video Processing
Machine Learning
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.
title Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging
topic Image and Video Processing
Machine Learning
url https://arxiv.org/abs/2512.06977