Reference-based Image Super-Resolution with Deformable Attention Transformer

TL;DR

This paper introduces DATSR, a deformable attention Transformer for reference-based image super-resolution, effectively matching and transferring textures from auxiliary images to enhance low-resolution images.

Contribution

The paper proposes a novel deformable attention Transformer architecture with multi-scale modules for improved texture matching and transfer in reference-based super-resolution.

Findings

Achieves state-of-the-art results on benchmark datasets.

Effectively matches textures between LR and Ref images.

Enhances visual quality of super-resolved images.

Abstract

Reference-based image super-resolution (RefSR) aims to exploit auxiliary reference (Ref) images to super-resolve low-resolution (LR) images. Recently, RefSR has been attracting great attention as it provides an alternative way to surpass single image SR. However, addressing the RefSR problem has two critical challenges: (i) It is difficult to match the correspondence between LR and Ref images when they are significantly different; (ii) How to transfer the relevant texture from Ref images to compensate the details for LR images is very challenging. To address these issues of RefSR, this paper proposes a deformable attention Transformer, namely DATSR, with multiple scales, each of which consists of a texture feature encoder (TFE) module, a reference-based deformable attention (RDA) module and a residual feature aggregation (RFA) module. Specifically, TFE first extracts image transformation (e.g., brightness) insensitive features for LR and Ref images, RDA then can exploit multiple relevant textures to compensate more information for LR features, and RFA lastly aggregates LR features and relevant textures to get a more visually pleasant result. Extensive experiments demonstrate that our DATSR achieves state-of-the-art performance on benchmark datasets quantitatively and qualitatively.