Postprocessing of Compressed Images via Sequential Denoising

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.

Submitted to IEEE Transactions on Image Processing

References in corpus (1)

• Deep Learning in Neural Networks: An Overview

Cited by in corpus (6)

• MuLoG, or How to apply Gaussian denoisers to multi-channel SAR speckle reduction?
• Better Compression with Deep Pre-Editing
• A New Recurrent Plug-and-Play Prior Based on the Multiple Self-Similarity Network
• Restoration by Compression
• Optimized Pre-Compensating Compression
• Deep Model-Based Super-Resolution with Non-uniform Blur