collaborators

5 papers

cs.CV2026

MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction

Seunghoi Kim, Chen Jin, Henry F. J. Tregidgo +2

Zero-shot MRI reconstruction relies on generative priors, but single-modality unconditional priors produce hallucinations under severe ill-posedness. In many clinical workflows, co…

cs.CV2026

Trustworthy MRI Reconstruction via Bayesian Uncertainty Quantification with Sparsity Prior Models

Ahmed Karam Eldaly, Matteo Figini, Daniel C. Alexander

We propose a novel Bayesian framework for joint image reconstruction and uncertainty quantification from compressed sensing magnetic resonance imaging data. The problem is formulat…

eess.IV2026

Bayesian Uncertainty-Aware MRI Reconstruction

Ahmed Karam Eldaly, Matteo Figini, Daniel C. Alexander

We propose a novel framework for joint magnetic resonance image reconstruction and uncertainty quantification using under-sampled k-space measurements. The problem is formulated as…

cs.CV2025

HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration

Seunghoi Kim, Henry F. J. Tregidgo, Chen Jin +2

Generative models are prone to hallucinations: plausible but incorrect structures absent in the ground truth. This issue is problematic in image restoration for safety-critical dom…

eess.IV2025

Tackling Hallucination from Conditional Models for Medical Image Reconstruction with DynamicDPS

Seunghoi Kim, Henry F. J. Tregidgo, Matteo Figini +3

Hallucinations are spurious structures not present in the ground truth, posing a critical challenge in medical image reconstruction, especially for data-driven conditional models.…