Inverse problems appear in many image processing applications and are usually addressed by designing task-specific algorithms. The recently proposed Plug-and-Play (P&P) framework allows solving general inverse problems by leveraging the impressive capabilities of existing denoising techniques. However, P&P often requires a burdensome parameter tuning. We propose an alternative method for solving inverse problems using denoising algorithms that require less parameter tuning. We demonstrate its competitiveness with task-specific techniques and P&P for image inpainting and deblurring.

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:

Raja Giryes (Tel Aviv University)

Tom Tirer (Tel Aviv University)

Keywords:

image deblurring, image reconstruction, inverse problems