# MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution

arXiv: https://arxiv.org/abs/2106.02299 · HTML: https://mlsanity.com/paper/2106.02299/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 4 Jun 2021.

## Builds on (most cited first, 27 of 27)

- [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)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (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)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [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)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Learning Texture Transformer Network for Image Super-Resolution](https://mlsanity.com/paper/2006.04139/) (2020)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [The relativistic discriminator: a key element missing from standard GAN](https://mlsanity.com/paper/1807.00734/) (2018)
- [EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis](https://mlsanity.com/paper/1612.07919/) (2016)
- [The Contextual Loss for Image Transformation with Non-Aligned Data](https://mlsanity.com/paper/1803.02077/) (2018)
- [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)
- [LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond](https://mlsanity.com/paper/2105.10422/) (2021)
- [Image Inpainting via Generative Multi-column Convolutional Neural Networks](https://mlsanity.com/paper/1810.08771/) (2018)
- [Maintaining Natural Image Statistics with the Contextual Loss](https://mlsanity.com/paper/1803.04626/) (2018)

## Built on by (most cited first, 30 of 80)

- [ControlNeXt: Powerful and Efficient Control for Image and Video Generation](https://mlsanity.com/paper/2408.06070/) (2024)
- [Blind Image Super-Resolution: A Survey and Beyond](https://mlsanity.com/paper/2107.03055/) (2021)
- [Any-resolution Training for High-resolution Image Synthesis](https://mlsanity.com/paper/2204.07156/) (2022)
- [CoSeR: Bridging Image and Language for Cognitive Super-Resolution](https://mlsanity.com/paper/2311.16512/) (2023)
- [Reference-based Image Super-Resolution with Deformable Attention Transformer](https://mlsanity.com/paper/2207.11938/) (2022)
- [AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling](https://mlsanity.com/paper/2111.00772/) (2021)
- [HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance](https://mlsanity.com/paper/2307.07829/) (2023)
- [Improving Image Restoration through Removing Degradations in Textual Representations](https://mlsanity.com/paper/2312.17334/) (2023)
- [Transformer-empowered Multi-scale Contextual Matching and Aggregation for Multi-contrast MRI Super-resolution](https://mlsanity.com/paper/2203.13963/) (2022)
- [Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution](https://mlsanity.com/paper/2404.04785/) (2024)
- [DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution](https://mlsanity.com/paper/2303.13933/) (2023)
- [DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation](https://mlsanity.com/paper/2207.06124/) (2022)
- [Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations](https://mlsanity.com/paper/2203.01325/) (2022)
- [Cross-Modality High-Frequency Transformer for MR Image Super-Resolution](https://mlsanity.com/paper/2203.15314/) (2022)
- [Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model](https://mlsanity.com/paper/2403.17460/) (2024)
- [Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution](https://mlsanity.com/paper/2201.04358/) (2022)
- [ReFIR: Grounding Large Restoration Models with Retrieval Augmentation](https://mlsanity.com/paper/2410.05601/) (2024)
- [Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution](https://mlsanity.com/paper/2406.13607/) (2024)
- [Global Learnable Attention for Single Image Super-Resolution](https://mlsanity.com/paper/2212.01057/) (2022)
- [Attention-based Multi-Reference Learning for Image Super-Resolution](https://mlsanity.com/paper/2108.13697/) (2021)
- [RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection](https://mlsanity.com/paper/2211.04203/) (2022)
- [LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution](https://mlsanity.com/paper/2303.04970/) (2023)
- [HIPA: Hierarchical Patch Transformer for Single Image Super Resolution](https://mlsanity.com/paper/2203.10247/) (2022)
- [Reference-based Image and Video Super-Resolution via C2-Matching](https://mlsanity.com/paper/2212.09581/) (2022)
- [Recurrent Self-Supervised Video Denoising with Denser Receptive Field](https://mlsanity.com/paper/2308.03608/) (2023)
- [RefQSR: Reference-based Quantization for Image Super-Resolution Networks](https://mlsanity.com/paper/2404.01690/) (2024)
- [Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images](https://mlsanity.com/paper/2302.12491/) (2023)
- [Deep Unfolding Convolutional Dictionary Model for Multi-Contrast MRI Super-resolution and Reconstruction](https://mlsanity.com/paper/2309.01171/) (2023)
- [BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution](https://mlsanity.com/paper/2502.20943/) (2025)
- [Reference-Guided Texture and Structure Inference for Image Inpainting](https://mlsanity.com/paper/2207.14498/) (2022)

## Abstract (arXiv)

Reference-based image super-resolution (RefSR) has shown promising success in recovering high-frequency details by utilizing an external reference image (Ref). In this task, texture details are transferred from the Ref image to the low-resolution (LR) image according to their point- or patch-wise correspondence. Therefore, high-quality correspondence matching is critical. It is also desired to be computationally efficient. Besides, existing RefSR methods tend to ignore the potential large disparity in distributions between the LR and Ref images, which hurts the effectiveness of the information utilization. In this paper, 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. This scheme makes the network robust to handle different reference images. Extensive quantitative and qualitative experiments validate the effectiveness of our proposed model.