# Postprocessing of Compressed Images via Sequential Denoising

arXiv: https://arxiv.org/abs/1510.09041 · HTML: https://mlsanity.com/paper/1510.09041/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2015.

## Built on by (most cited first, 8 of 8)

- [Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --](https://mlsanity.com/paper/2301.03362/) (2023)
- [Multi-modality Deep Restoration of Extremely Compressed Face Videos](https://mlsanity.com/paper/2107.05548/) (2021)
- [Deep Model-Based Super-Resolution with Non-uniform Blur](https://mlsanity.com/paper/2204.10109/) (2022)
- [CurvPnP: Plug-and-play Blind Image Restoration with Deep Curvature Denoiser](https://mlsanity.com/paper/2211.07286/) (2022)
- [Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion](https://mlsanity.com/paper/2302.06096/) (2023)
- [How Much Training Data is Memorized in Overparameterized Autoencoders? An Inverse Problem Perspective on Memorization Evaluation](https://mlsanity.com/paper/2310.02897/) (2023)
- [Video Restoration with a Deep Plug-and-Play Prior](https://mlsanity.com/paper/2209.02854/) (2022)
- [Fast and Robust Sparsity-Aware Block Diagonal Representation](https://mlsanity.com/paper/2312.01137/) (2023)

## Abstract (arXiv)

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.