CISRNet: Compressed Image Super-Resolution Network

TL;DR

CISRNet is a two-stage deep learning framework designed to improve super-resolution of compressed images by effectively reducing compression artifacts and enhancing image quality.

Contribution

The paper introduces CISRNet, a novel coarse-to-fine network architecture specifically optimized for compressed image super-resolution tasks.

Findings

CISRNet outperforms existing SISR methods on compressed images.

The two-stage framework effectively reduces compression artifacts.

Recursive and residual learning improve super-resolution quality.

Abstract

In recent years, tons of research has been conducted on Single Image Super-Resolution (SISR). However, to the best of our knowledge, few of these studies are mainly focused on compressed images. A problem such as complicated compression artifacts hinders the advance of this study in spite of its high practical values. To tackle this problem, we proposed CISRNet; a network that employs a two-stage coarse-to-fine learning framework that is mainly optimized for Compressed Image Super-Resolution Problem. Specifically, CISRNet consists of two main subnetworks; the coarse and refinement network, where recursive and residual learning is employed within these two networks respectively. Extensive experiments show that with a careful design choice, CISRNet performs favorably against competing Single-Image Super-Resolution methods in the Compressed Image Super-Resolution tasks.