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

• URL: http://arxiv.org/abs/2508.09449v1
• Date: Wed, 13 Aug 2025 03:05:20 GMT
• Title: RASR: Retrieval-Augmented Super Resolution for Practical Reference-based Image Restoration
• Authors: Jiaqi Yan, Shuning Xu, Xiangyu Chen, Dell Zhang, Jie Tang, Gangshan Wu, Jie Liu,
• Abstract summary: RefSR improves upon Single Image Super Resolution (SISR) by leveraging high-quality reference images to enhance texture fidelity and visual realism.<n>Existing RefSR approaches rely on manually curated target-reference image pairs.<n>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.
• Score: 41.50858324338511
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• RefSR-Adv: Adversarial Attack on Reference-based Image Super-Resolution Models [0.0]
  RefSR-Adv is an adversarial attack that degrades SR outputs by perturbing only the reference image.<n> experiments confirm a positive correlation between the similarity of the low-resolution input and the reference image and attack effectiveness.<n>This study reveals a security vulnerability in RefSR systems, aiming to urge researchers to pay attention to the robustness of RefSR.
  arXiv  Detail & Related papers  (2026-01-03T14:59:15Z)
• Dual-domain Adaptation Networks for Realistic Image Super-resolution [81.34345637776408]
  Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones.<n>Current methods struggle with limited real-world LR-HR data, impacting the learning of basic image features.<n>We introduce a novel approach, which is able to efficiently adapt pre-trained image SR models from simulated to real-world datasets.
  arXiv  Detail & Related papers  (2025-11-21T12:57:23Z)
• Ultra-High-Definition Reference-Based Landmark Image Super-Resolution with Generative Diffusion Prior [16.01061302804634]
  RefSR aims to restore a low-resolution (LR) image by utilizing the semantic and texture information from an additional reference high-resolution (reference HR) image.<n>Existing diffusion-based RefSR methods are typically built upon ControlNet.<n>We propose TriFlowSR, a novel framework that explicitly achieves pattern matching between the LR image and the reference HR image.
  arXiv  Detail & Related papers  (2025-08-14T16:04:39Z)
• Controllable Reference-Based Real-World Remote Sensing Image Super-Resolution with Generative Diffusion Priors [13.148815217684277]
  Super-resolution (SR) techniques can enhance the spatial resolution of remote sensing images by utilizing low-resolution (LR) images to reconstruct high-resolution (HR) images.<n>Existing RefSR methods struggle with real-world complexities, such as cross-sensor resolution gap and significant land cover changes.<n>We propose CRefDiff, a novel controllable reference-based diffusion model for real-world remote sensing image SR.
  arXiv  Detail & Related papers  (2025-06-30T12:45:28Z)
• RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution [57.98314517861539]
  Burst super-resolution (BurstSR) aims at reconstructing a high-resolution (HR) image from a sequence of low-resolution (LR) and noisy images. In this paper, we suggest fusing cues frame-by-frame with an efficient and flexible recurrent network.
  arXiv  Detail & Related papers  (2023-06-30T12:14:13Z)
• A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-Resolution [29.57364804554312]
  Reference-based super-resolution (RefSR) has gained considerable success in the field of super-resolution. We propose a feature reuse framework that guides the step-by-step texture reconstruction process. We introduce a single image feature embedding module and a texture-adaptive aggregation module.
  arXiv  Detail & Related papers  (2023-06-02T12:49:22Z)
• RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection [66.08293086254851]
  We propose a reciprocal learning framework to reinforce the learning of a RefSR network. The newly proposed module aligns reference-input images at multi-scale feature spaces and performs reference-aware feature selection. We empirically show that multiple recent state-of-the-art RefSR models can be consistently improved with our reciprocal learning paradigm.
  arXiv  Detail & Related papers  (2022-11-08T12:39:35Z)
• RZSR: Reference-based Zero-Shot Super-Resolution with Depth Guided Self-Exemplars [20.771851470271777]
  Single image super-resolution (SISR) has demonstrated outstanding performance in generating high-resolution (HR) images from low-resolution (LR) images. We propose an integrated solution, called reference-based zero-shot SR (RZSR)
  arXiv  Detail & Related papers  (2022-08-24T05:48:17Z)
• Reference-based Image Super-Resolution with Deformable Attention Transformer [62.71769634254654]
  RefSR aims to exploit auxiliary reference (Ref) images to super-resolve low-resolution (LR) images. This paper proposes a deformable attention Transformer, namely DATSR, with multiple scales. Experiments demonstrate that our DATSR achieves state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-07-25T07:07:00Z)
• MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution [74.24676600271253]
  We propose the MASA network for RefSR, where two novel modules are designed to address these problems. The proposed Match & Extraction Module significantly reduces the computational cost by a coarse-to-fine correspondence matching scheme. The Spatial Adaptation Module learns the difference of distribution between the LR and Ref images, and remaps the distribution of Ref features to that of LR features in a spatially adaptive way.
  arXiv  Detail & Related papers  (2021-06-04T07:15:32Z)
• Robust Reference-based Super-Resolution via C2-Matching [77.51610726936657]
  Super-Resolution (Ref-SR) has recently emerged as a promising paradigm to enhance a low-resolution (LR) input image by introducing an additional high-resolution (HR) reference image. Existing Ref-SR methods mostly rely on implicit correspondence matching to borrow HR textures from reference images to compensate for the information loss in input images. We propose C2-Matching, which produces explicit robust matching crossing transformation and resolution.
  arXiv  Detail & Related papers  (2021-06-03T16:40:36Z)
• Real-World Single Image Super-Resolution: A Brief Review [44.14123585227239]
  Single image super-resolution (SISR) aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) observation. Deep learning-based super-resolution approaches have drawn much attention and have greatly improved the reconstruction performance on synthetic data.
  arXiv  Detail & Related papers  (2021-03-03T12:41:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.