Blind Image Super-Resolution via Contrastive Representation Learning

TL;DR

This paper introduces CRL-SR, a contrastive learning-based method for blind image super-resolution that effectively handles multi-modal and spatially variant degradations, outperforming existing methods in quality and robustness.

Contribution

The paper proposes a novel contrastive representation learning framework for blind super-resolution, addressing multi-source and spatially variant degradation challenges.

Findings

CRL-SR outperforms state-of-the-art methods on synthetic datasets.

CRL-SR effectively handles real-world multi-modal degradations.

The method improves high-frequency detail recovery in super-resolved images.

Abstract

Image super-resolution (SR) research has witnessed impressive progress thanks to the advance of convolutional neural networks (CNNs) in recent years. However, most existing SR methods are non-blind and assume that degradation has a single fixed and known distribution (e.g., bicubic) which struggle while handling degradation in real-world data that usually follows a multi-modal, spatially variant, and unknown distribution. The recent blind SR studies address this issue via degradation estimation, but they do not generalize well to multi-source degradation and cannot handle spatially variant degradation. We design CRL-SR, a contrastive representation learning network that focuses on blind SR of images with multi-modal and spatially variant distributions. CRL-SR addresses the blind SR challenges from two perspectives. The first is contrastive decoupling encoding which introduces contrastive learning to extract resolution-invariant embedding and discard resolution-variant embedding under the guidance of a bidirectional contrastive loss. The second is contrastive feature refinement which generates lost or corrupted high-frequency details under the guidance of a conditional contrastive loss. Extensive experiments on synthetic datasets and real images show that the proposed CRL-SR can handle multi-modal and spatially variant degradation effectively under blind settings and it also outperforms state-of-the-art SR methods qualitatively and quantitatively.