RASR: Retrieval-Augmented Super Resolution for Practical Reference-based Image Restoration

TL;DR

RASR introduces a retrieval-augmented super resolution method that automatically retrieves relevant high-resolution references for low-quality images, enabling practical and scalable reference-based image restoration in real-world scenarios.

Contribution

It proposes RASR, a novel retrieval-augmented framework and dataset for practical reference-based super resolution, addressing the limitations of manual reference pairing in existing methods.

Findings

RASRNet outperforms SISR baselines in PSNR and LPIPS metrics.

The RASR-Flickr30 dataset supports open-world retrieval for diverse categories.

Retrieval augmentation improves texture realism and visual quality.

Abstract

Reference-based Super Resolution (RefSR) improves upon Single Image Super Resolution (SISR) by leveraging high-quality reference images to enhance texture fidelity and visual realism. However, a critical limitation of existing RefSR approaches is their reliance on manually curated target-reference image pairs, which severely constrains their practicality in real-world scenarios. To overcome this, we introduce Retrieval-Augmented Super Resolution (RASR), a new and practical RefSR paradigm that automatically retrieves semantically relevant high-resolution images from a reference database given only a low-quality input. This enables scalable and flexible RefSR in realistic use cases, such as enhancing mobile photos taken in environments like zoos or museums, where category-specific reference data (e.g., animals, artworks) can be readily collected or pre-curated. To facilitate research in this direction, we construct RASR-Flickr30, the first benchmark dataset designed for RASR. Unlike prior datasets with fixed target-reference pairs, RASR-Flickr30 provides per-category reference databases to support open-world retrieval. We further propose RASRNet, a strong baseline that combines a semantic reference retriever with a diffusion-based RefSR generator. It retrieves relevant references based on semantic similarity and employs a diffusion-based generator enhanced with semantic conditioning. Experiments on RASR-Flickr30 demonstrate that RASRNet consistently improves over SISR baselines, achieving +0.38 dB PSNR and -0.0131 LPIPS, while generating more realistic textures. These findings highlight retrieval augmentation as a promising direction to bridge the gap between academic RefSR research and real-world applicability.