Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction

arXiv:2403.17042v1 Announce Type: cross
Abstract: In a great number of tasks in science and engineering, the goal is to infer an unknown image from a small number of measurements collected from a known forward model describing certain sensing or imaging modality. Due to resource constraints, this task is often extremely ill-posed, which necessitates the adoption of expressive prior information to regularize the solution space. Score-based diffusion models, due to its impressive empirical success, have emerged as an appealing candidate of …

abstract arxiv constraints cs.cv cs.lg diffusion eess.iv eess.sp engineering image imaging math.oc posterior robust sampling science sensing small stat.ml tasks type