CISRDCNN: Super-resolution of compressed images using deep convolutional neural networks

TL;DR

This paper introduces CISRDCNN, an end-to-end deep learning model that simultaneously reduces compression artifacts and enhances resolution in compressed images, outperforming existing methods especially on JPEG images.

Contribution

The paper presents a novel deep CNN that jointly addresses artifact reduction and super-resolution in a single end-to-end framework, improving over sequential approaches.

Findings

Achieves state-of-the-art super-resolution performance on compressed images.

Effectively enhances quality of real low-quality web images.

Improves rate-distortion performance in low bit-rate image coding.

Abstract

In recent years, much research has been conducted on image super-resolution (SR). To the best of our knowledge, however, few SR methods were concerned with compressed images. The SR of compressed images is a challenging task due to the complicated compression artifacts, while many images suffer from them in practice. The intuitive solution for this difficult task is to decouple it into two sequential but independent subproblems, i.e., compression artifacts reduction (CAR) and SR. Nevertheless, some useful details may be removed in CAR stage, which is contrary to the goal of SR and makes the SR stage more challenging. In this paper, an end-to-end trainable deep convolutional neural network is designed to perform SR on compressed images (CISRDCNN), which reduces compression artifacts and improves image resolution jointly. Experiments on compressed images produced by JPEG (we take the JPEG as an example in this paper) demonstrate that the proposed CISRDCNN yields state-of-the-art SR performance on commonly used test images and imagesets. The results of CISRDCNN on real low quality web images are also very impressive, with obvious quality enhancement. Further, we explore the application of the proposed SR method in low bit-rate image coding, leading to better rate-distortion performance than JPEG.