CAS-CNN: A Deep Convolutional Neural Network for Image Compression Artifact Suppression

TL;DR

This paper introduces a 12-layer deep convolutional neural network designed to effectively reduce compression artifacts in images, outperforming traditional JPEG and previous neural network methods in PSNR improvements.

Contribution

The paper presents a novel deep CNN architecture with hierarchical skip connections and multi-scale loss for artifact suppression, achieving state-of-the-art results across various quality factors.

Findings

Up to 1.79 dB PSNR boost over JPEG

Up to 0.36 dB PSNR improvement over previous ConvNet methods

Single network trained at QF 60 generalizes well across QF 40-76

Abstract

Lossy image compression algorithms are pervasively used to reduce the size of images transmitted over the web and recorded on data storage media. However, we pay for their high compression rate with visual artifacts degrading the user experience. Deep convolutional neural networks have become a widespread tool to address high-level computer vision tasks very successfully. Recently, they have found their way into the areas of low-level computer vision and image processing to solve regression problems mostly with relatively shallow networks. We present a novel 12-layer deep convolutional network for image compression artifact suppression with hierarchical skip connections and a multi-scale loss function. We achieve a boost of up to 1.79 dB in PSNR over ordinary JPEG and an improvement of up to 0.36 dB over the best previous ConvNet result. We show that a network trained for a specific quality factor (QF) is resilient to the QF used to compress the input image - a single network trained for QF 60 provides a PSNR gain of more than 1.5 dB over the wide QF range from 40 to 76.