Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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.

Laurentius Valdy, Richard D. Paul, Alessio Quercia, Zhuo Cao, Xuan Zhao, Hanno Scharr, Arya Bangun• 2025

Related benchmarks

TaskDatasetResultRank
4D-STEM Phase Projection ReconstructionHexagonal Crystal Data
SSIM0.981
5
MRI Volume ReconstructionRoots MRI
SSIM81.3
5
Volume ReconstructionBRATS MRI t1ce 20 (train)
SSIM0.968
5
Volume ReconstructionCubic Crystal Data CoPt3, Tb3InC
SSIM89.9
5
Showing 4 of 4 rows

Other info

Follow for update