# LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution

arXiv: https://arxiv.org/abs/2303.04970 · HTML: https://mlsanity.com/paper/2303.04970/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [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)
- [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)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Learning Texture Transformer Network for Image Super-Resolution](https://mlsanity.com/paper/2006.04139/) (2020)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [Non-Local Recurrent Network for Image Restoration](https://mlsanity.com/paper/1806.02919/) (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)
- [MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution](https://mlsanity.com/paper/2106.02299/) (2021)
- [Robust Reference-based Super-Resolution via C2-Matching](https://mlsanity.com/paper/2106.01863/) (2021)
- [Reference-based Image Super-Resolution with Deformable Attention Transformer](https://mlsanity.com/paper/2207.11938/) (2022)
- [Super-Identity Convolutional Neural Network for Face Hallucination](https://mlsanity.com/paper/1811.02328/) (2018)
- [Dual-Camera Super-Resolution with Aligned Attention Modules](https://mlsanity.com/paper/2109.01349/) (2021)
- [Reference-based Video Super-Resolution Using Multi-Camera Video Triplets](https://mlsanity.com/paper/2203.14537/) (2022)
- [Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution](https://mlsanity.com/paper/2201.04358/) (2022)
- [RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection](https://mlsanity.com/paper/2211.04203/) (2022)

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

- [ReFIR: Grounding Large Restoration Models with Retrieval Augmentation](https://mlsanity.com/paper/2410.05601/) (2024)
- [Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors](https://mlsanity.com/paper/2407.09919/) (2024)
- [Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling](https://mlsanity.com/paper/2602.01864/) (2026)
- [MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References](https://mlsanity.com/paper/2407.13745/) (2024)
- [An Anisotropic Cross-View Texture Transfer with Multi-Reference Non-Local Attention for CT Slice Interpolation](https://mlsanity.com/paper/2509.20242/) (2025)
- [Reference-based OCT Angiogram Super-resolution with Learnable Texture Generation](https://mlsanity.com/paper/2305.05835/) (2023)
- [The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregation](https://mlsanity.com/paper/2401.08123/) (2024)
- [GMT: Enhancing Generalizable Neural Rendering via Geometry-Driven Multi-Reference Texture Transfer](https://mlsanity.com/paper/2410.00672/) (2024)
- [RASR: Retrieval-Augmented Super Resolution for Practical Reference-based Image Restoration](https://mlsanity.com/paper/2508.09449/) (2025)
- [LiveMoments: Reselected Key Photo Restoration in Live Photos via Reference-guided Diffusion](https://mlsanity.com/paper/2604.12286/) (2026)
- [Perceiving Better Moments: Cover Frame Reselection and Enhancement for Live Photos with the Live2K Dataset](https://mlsanity.com/paper/2607.04151/) (2026)
- [Reference-Based Face Super-Resolution Using the Spatial Transformer](https://mlsanity.com/paper/2607.11025/) (2026)

## Abstract (arXiv)

It is widely agreed that reference-based super-resolution (RefSR) achieves superior results by referring to similar high quality images, compared to single image super-resolution (SISR). Intuitively, the more references, the better performance. However, previous RefSR methods have all focused on single-reference image training, while multiple reference images are often available in testing or practical applications. The root cause of such training-testing mismatch is the absence of publicly available multi-reference SR training datasets, which greatly hinders research efforts on multi-reference super-resolution. To this end, we construct a large-scale, multi-reference super-resolution dataset, named LMR. It contains 112,142 groups of 300x300 training images, which is 10x of the existing largest RefSR dataset. The image size is also much larger. More importantly, each group is equipped with 5 reference images with different similarity levels. Furthermore, we propose a new baseline method for multi-reference super-resolution: MRefSR, including a Multi-Reference Attention Module (MAM) for feature fusion of an arbitrary number of reference images, and a Spatial Aware Filtering Module (SAFM) for the fused feature selection. The proposed MRefSR achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations. Our code and data would be made available soon.