Blind Super Resolution with Reference Images and Implicit Degradation Representation

TL;DR

This paper introduces a novel blind super-resolution method that uses HR reference images to adaptively model degradation kernels considering scale factors, leading to improved SR performance.

Contribution

It proposes a scale-aware, reference-based approach that jointly models degradation and scaling factors, enhancing blind super-resolution methods.

Findings

Outperforms previous methods in blind SR tasks

Effective for both trained and zero-shot SR models

Utilizes HR references to adaptively learn degradation kernels

Abstract

Previous studies in blind super-resolution (BSR) have primarily concentrated on estimating degradation kernels directly from low-resolution (LR) inputs to enhance super-resolution. However, these degradation kernels, which model the transition from a high-resolution (HR) image to its LR version, should account for not only the degradation process but also the downscaling factor. Applying the same degradation kernel across varying super-resolution scales may be impractical. Our research acknowledges degradation kernels and scaling factors as pivotal elements for the BSR task and introduces a novel strategy that utilizes HR images as references to establish scale-aware degradation kernels. By employing content-irrelevant HR reference images alongside the target LR image, our model adaptively discerns the degradation process. It is then applied to generate additional LR-HR pairs through down-sampling the HR reference images, which are keys to improving the SR performance. Our reference-based training procedure is applicable to proficiently trained blind SR models and zero-shot blind SR methods, consistently outperforming previous methods in both scenarios. This dual consideration of blur kernels and scaling factors, coupled with the use of a reference image, contributes to the effectiveness of our approach in blind super-resolution tasks.