Joint Learning Content and Degradation Aware Feature for Blind Super-Resolution

TL;DR

This paper introduces CDSR, a novel blind super-resolution network that jointly learns content and degradation features, effectively addressing degradation inconsistency and outperforming existing methods on benchmarks.

Contribution

The paper proposes a joint learning framework with three new modules to improve blind image super-resolution by better modeling content and degradation features.

Findings

Outperforms existing UDP models in benchmarks

Achieves competitive PSNR and SSIM scores with state-of-the-art SKP methods

Effectively reduces degradation feature and SR feature inconsistency

Abstract

To achieve promising results on blind image super-resolution (SR), some attempts leveraged the low resolution (LR) images to predict the kernel and improve the SR performance. However, these Supervised Kernel Prediction (SKP) methods are impractical due to the unavailable real-world blur kernels. Although some Unsupervised Degradation Prediction (UDP) methods are proposed to bypass this problem, the \textit{inconsistency} between degradation embedding and SR feature is still challenging. By exploring the correlations between degradation embedding and SR feature, we observe that jointly learning the content and degradation aware feature is optimal. Based on this observation, a Content and Degradation aware SR Network dubbed CDSR is proposed. Specifically, CDSR contains three newly-established modules: (1) a Lightweight Patch-based Encoder (LPE) is applied to jointly extract content and degradation features; (2) a Domain Query Attention based module (DQA) is employed to adaptively reduce the inconsistency; (3) a Codebook-based Space Compress module (CSC) that can suppress the redundant information. Extensive experiments on several benchmarks demonstrate that the proposed CDSR outperforms the existing UDP models and achieves competitive performance on PSNR and SSIM even compared with the state-of-the-art SKP methods.