Postprocessing of Compressed Images via Sequential Denoising

TL;DR

This paper introduces a novel postprocessing method for reducing compression artifacts in images by framing it as an inverse problem and leveraging advanced denoising algorithms within a regularized optimization framework, achieving significant quality improvements.

Contribution

It proposes a new postprocessing technique using the Plug-and-Play Prior framework with ADMM, incorporating a linearization of compression processes for enhanced artifact reduction.

Findings

Effective artifact reduction for JPEG, JPEG2000, and HEVC.

Significant improvements in image quality demonstrated.

Versatile approach applicable to various transform coding methods.

Abstract

In this work we propose a novel postprocessing technique for compression-artifact reduction. Our approach is based on posing this task as an inverse problem, with a regularization that leverages on existing state-of-the-art image denoising algorithms. We rely on the recently proposed Plug-and-Play Prior framework, suggesting the solution of general inverse problems via Alternating Direction Method of Multipliers (ADMM), leading to a sequence of Gaussian denoising steps. A key feature in our scheme is a linearization of the compression-decompression process, so as to get a formulation that can be optimized. In addition, we supply a thorough analysis of this linear approximation for several basic compression procedures. The proposed method is suitable for diverse compression techniques that rely on transform coding. Specifically, we demonstrate impressive gains in image quality for several leading compression methods - JPEG, JPEG2000, and HEVC.