Content-decoupled Contrastive Learning-based Implicit Degradation Modeling for Blind Image Super-Resolution

TL;DR

This paper introduces a novel blind super-resolution framework that uses content-decoupled contrastive learning to improve degradation modeling, resulting in better performance and reduced complexity in diverse scenarios.

Contribution

It proposes a negative-free contrastive learning method with a cyclic shift sampling strategy for implicit degradation modeling in blind SR.

Findings

Achieves competitive results on synthetic and real data.

Reduces model complexity and computational costs.

Enhances degradation representation discriminability.

Abstract

Implicit degradation modeling-based blind super-resolution (SR) has attracted more increasing attention in the community due to its excellent generalization to complex degradation scenarios and wide application range. How to extract more discriminative degradation representations and fully adapt them to specific image features is the key to this task. In this paper, we propose a new Content-decoupled Contrastive Learning-based blind image super-resolution (CdCL) framework following the typical blind SR pipeline. This framework introduces negative-free contrastive learning technique for the first time to model the implicit degradation representation, in which a new cyclic shift sampling strategy is designed to ensure decoupling between content features and degradation features from the data perspective, thereby improving the purity and discriminability of the learned implicit degradation space. In addition, we propose a detail-aware implicit degradation adapting module that can better adapt degradation representations to specific LR features by enhancing the basic adaptation unit's perception of image details, significantly reducing the overall SR model complexity. Extensive experiments on synthetic and real data show that our method achieves highly competitive quantitative and qualitative results in various degradation settings while obviously reducing parameters and computational costs, validating the feasibility of designing practical and lightweight blind SR tools.