DART and DRIFT Diffusion Priors for MRI and 4D-STEM
Figure 1: Data acquisition of a brain in MRI (k-space) and 4D-STEM (diffraction patterns) of crystalline materials, as well as proposed methods: DART (alternating update between trained diffusion prior and physics constraints) and DRIFT (diffusion priors as initialization before applying physical constraints). Physical constraints 𝒢 ( X ) \mathcal{G}(\emph{X}) are adapted depending on the modality (MRI or 4D-STEM).
Paper context
Paper title: Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging 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. Passages referencing this figure: de/ias-8/Distributed˙3DDM Background Figure 1: Data acquisition of a brain in MRI (k-space) and 4D-STEM (diffraction patterns) of crystalline materials, as well as proposed methods: DART (alternating update between trained diffusion prior and physics constraints) and DRIFT (diffusion priors as initialization before applying physical constraints). The acquisition process for both undersampled MRI and 4D-STEM are shown in Figure 1 . The inference procedure is summarized in Algorithm 1 , as well as in Figure 1 where the main difference between DART and DRIFT is visualized. To guarantee the reconstruction of each measurement data for MRI (k-space) and 4D-STEM (diffraction patterns), it should be incorporated in the inference process, as presented in Figure 1 .
