# Attention-based Multi-Reference Learning for Image Super-Resolution

arXiv: https://arxiv.org/abs/2108.13697 · HTML: https://mlsanity.com/paper/2108.13697/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 31 Aug 2021.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Deep Learning for Image Super-resolution: A Survey](https://mlsanity.com/paper/1902.06068/) (2019)
- [Learning Texture Transformer Network for Image Super-Resolution](https://mlsanity.com/paper/2006.04139/) (2020)
- [RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution](https://mlsanity.com/paper/1908.06382/) (2019)
- [Residual Feature Distillation Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2009.11551/) (2020)
- [Image Super-Resolution by Neural Texture Transfer](https://mlsanity.com/paper/1903.00834/) (2019)
- [CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping](https://mlsanity.com/paper/1807.10547/) (2018)
- [MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution](https://mlsanity.com/paper/2106.02299/) (2021)
- [Wide Activation for Efficient and Accurate Image Super-Resolution](https://mlsanity.com/paper/1808.08718/) (2018)
- [3D Appearance Super-Resolution with Deep Learning](https://mlsanity.com/paper/1906.00925/) (2019)
- [Learned Multi-View Texture Super-Resolution](https://mlsanity.com/paper/2001.04775/) (2020)

## Built on by (most cited first, 12 of 12)

- [Reference-based Image Super-Resolution with Deformable Attention Transformer](https://mlsanity.com/paper/2207.11938/) (2022)
- [Imaging for All-Day Wearable Smart Glasses](https://mlsanity.com/paper/2504.13060/) (2025)
- [Super-resolution 3D Human Shape from a Single Low-Resolution Image](https://mlsanity.com/paper/2208.10738/) (2022)
- [BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution](https://mlsanity.com/paper/2502.20943/) (2025)
- [Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization](https://mlsanity.com/paper/2208.01587/) (2022)
- [MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References](https://mlsanity.com/paper/2407.13745/) (2024)
- [DRM-IR: Task-Adaptive Deep Unfolding Network for All-In-One Image Restoration](https://mlsanity.com/paper/2307.07688/) (2023)
- [RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionar](https://mlsanity.com/paper/2308.08721/) (2023)
- [Efficient Hybrid Zoom using Camera Fusion on Mobile Phones](https://mlsanity.com/paper/2401.01461/) (2024)
- [UltraZoom: Generating Gigapixel Images from Regular Photos](https://mlsanity.com/paper/2506.13756/) (2025)
- [Multi-Reference Image Super-Resolution: A Posterior Fusion Approach](https://mlsanity.com/paper/2212.09988/) (2022)
- [GMT: Enhancing Generalizable Neural Rendering via Geometry-Driven Multi-Reference Texture Transfer](https://mlsanity.com/paper/2410.00672/) (2024)

## Abstract (arXiv)

This paper proposes a novel Attention-based Multi-Reference Super-resolution network (AMRSR) that, given a low-resolution image, learns to adaptively transfer the most similar texture from multiple reference images to the super-resolution output whilst maintaining spatial coherence. The use of multiple reference images together with attention-based sampling is demonstrated to achieve significantly improved performance over state-of-the-art reference super-resolution approaches on multiple benchmark datasets. Reference super-resolution approaches have recently been proposed to overcome the ill-posed problem of image super-resolution by providing additional information from a high-resolution reference image. Multi-reference super-resolution extends this approach by providing a more diverse pool of image features to overcome the inherent information deficit whilst maintaining memory efficiency. A novel hierarchical attention-based sampling approach is introduced to learn the similarity between low-resolution image features and multiple reference images based on a perceptual loss. Ablation demonstrates the contribution of both multi-reference and hierarchical attention-based sampling to overall performance. Perceptual and quantitative ground-truth evaluation demonstrates significant improvement in performance even when the reference images deviate significantly from the target image. The project website can be found at https://marcopesavento.github.io/AMRSR/