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

Image credit: Laurentius Valdy & Arya Bangun & Alessio Quercia

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 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.

Publication
In IEEE International Conference on Acoustics, Speech and Signal Processing 2026
Alessio Quercia
Alessio Quercia
Research Associate @ Forschungszentrum Juelich | CS PhD | ex IBM Research Zurich, WSense

Alessio is a Research Associate at the Machine Learning and Data Analytics Institute (IAS-8) in Forschungszentrum Jülich. His research focus spans Data Efficient Learning, Multi-Task Learning, Transfer Learning, and Parameter-Efficient Fine-Tuning.

Related