Detail-Enhancing Framework for Reference-Based Image Super-Resolution

TL;DR

This paper introduces a Detail-Enhancing Framework for reference-based image super-resolution that leverages diffusion models to improve detail generation and alignment, leading to better visual quality without sacrificing numerical accuracy.

Contribution

The proposed framework uniquely combines diffusion models with reference-based super-resolution to enhance details and alignment, addressing limitations of previous methods.

Findings

Achieves superior visual quality in super-resolution tasks.

Maintains comparable numerical performance to existing methods.

Effectively handles cases with and without corresponding reference parts.

Abstract

Recent years have witnessed the prosperity of reference-based image super-resolution (Ref-SR). By importing the high-resolution (HR) reference images into the single image super-resolution (SISR) approach, the ill-posed nature of this long-standing field has been alleviated with the assistance of texture transferred from reference images. Although the significant improvement in quantitative and qualitative results has verified the superiority of Ref-SR methods, the presence of misalignment before texture transfer indicates room for further performance improvement. Existing methods tend to neglect the significance of details in the context of comparison, therefore not fully leveraging the information contained within low-resolution (LR) images. In this paper, we propose a Detail-Enhancing Framework (DEF) for reference-based super-resolution, which introduces the diffusion model to generate and enhance the underlying detail in LR images. If corresponding parts are present in the reference image, our method can facilitate rigorous alignment. In cases where the reference image lacks corresponding parts, it ensures a fundamental improvement while avoiding the influence of the reference image. Extensive experiments demonstrate that our proposed method achieves superior visual results while maintaining comparable numerical outcomes.