RASR: Retrieval-augmented Super Resolution For Practical Reference-based Image Restoration

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 prio

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyan2025rasr

Related papers

• Refir: Grounding Large Restoration Models With Retrieval Augmentation (2024)0.00
• Resedis: A Dataset For Referring-based Object Search Across Large-scale Image Collections (2025)0.00
• Retrieve In Style: Unsupervised Facial Feature Transfer And Retrieval (2021)9.92
• SETR: A Two-stage Semantic-enhanced Framework For Zero-shot Composed Image Retrieval (2025)0.00
• Lrvs-fashion: Extending Visual Search With Referring Instructions (2023)0.00
• Composed Image Retrieval For Remote Sensing (2024)11.03
• Global Learnable Attention For Single Image Super-resolution (2022)11.76
• Patternnet: A Benchmark Dataset For Performance Evaluation Of Remote Sensing Image Retrieval (2017)19.98