Image Restoration by Iterative Denoising and Backward Projections

TL;DR

This paper introduces a new iterative denoising method for inverse image problems that reduces parameter tuning, combines a novel optimization framework with denoising, and demonstrates competitive results in image inpainting and deblurring.

Contribution

It presents a less parameter-dependent approach using off-the-shelf denoisers within a novel optimization scheme for inverse problems.

Findings

Achieves high-quality image restoration with minimal parameter tuning.

Demonstrates competitive performance against task-specific and Plug-and-Play methods.

Provides theoretical analysis supporting the proposed approach.

Abstract

Inverse problems appear in many applications, such as image deblurring and inpainting. The common approach to address them is to design a specific algorithm for each problem. The Plug-and-Play (P&P) framework, which has been recently introduced, allows solving general inverse problems by leveraging the impressive capabilities of existing denoising algorithms. While this fresh strategy has found many applications, a burdensome parameter tuning is often required in order to obtain high-quality results. In this work, we propose an alternative method for solving inverse problems using off-the-shelf denoisers, which requires less parameter tuning. First, we transform a typical cost function, composed of fidelity and prior terms, into a closely related, novel optimization problem. Then, we propose an efficient minimization scheme with a plug-and-play property, i.e., the prior term is handled solely by a denoising operation. Finally, we present an automatic tuning mechanism to set the method's parameters. We provide a theoretical analysis of the method, and empirically demonstrate its competitiveness with task-specific techniques and the P&P approach for image inpainting and deblurring.