3 papers
cs.LG2026
Sample-efficient evidence estimation of score based priors for model selection
Frederic Wang, Katherine L. Bouman
The choice of prior is central to solving ill-posed imaging inverse problems, making it essential to select one consistent with the measurements to avoid severe bias. In Bayesi…
cs.CV2026
Optimizing Diffusion Priors in Image Reconstruction from a Single Observation
Frederic Wang, Katherine L. Bouman
While diffusion priors generate high-quality posterior samples across many inverse problems, they are often trained on limited training sets or purely simulated data, thus inheriti…
eess.IV2025
Non-rigid Motion Correction for MRI Reconstruction via Coarse-To-Fine Diffusion Models
Frederic Wang, Jonathan I. Tamir
Magnetic Resonance Imaging (MRI) is highly susceptible to motion artifacts due to the extended acquisition times required for k-space sampling. These artifacts can compromise diagn…