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

TL;DR

This paper introduces a physics-guided diffusion prior framework for multi-slice reconstruction that reduces memory usage and enhances reconstruction quality across medical and scientific imaging modalities.

Contribution

It integrates partitioned diffusion priors with physics-based constraints to improve efficiency and generalization in multi-slice reconstruction tasks.

Findings

Reduces GPU memory usage significantly.

Outperforms physics-only and full reconstruction baselines.

Improves accuracy on both in-distribution and out-of-distribution data.

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.