Regularization-by-denoising (RED) is an image recovery framework recently proposed by Romano, Elad, and Milanfar that allows arbitrary denoiser subroutines to be used with arbitrary convex optimization algorithms to solve a wide range of image recovery problems. We provide new interpretations and new algorithmic solutions to RED, and demonstrate our methods on cardiac imaging via parallel MRI.

This presentation is part of Minisymposium “MS52 - A Denoiser Can Do Much More Than Just... Denoising (2 parts)”
organized by: Yaniv Romano (Technion - Israel Institute of Technology) , Peyman Milanfar (Google Research) , Michael Elad (The Technion - Israel Institute of Technology) .

Authors:

Phil Schniter (The Ohio State University)

Ahmad Rizwan (The Ohio State University )

Edward Reehorst (The Ohio State University )

Adam Rich (The Ohio State University, United States)

Keywords:

image enhancement, image reconstruction, inverse problems