# A Lightweight Image Super-Resolution Transformer Trained on Low-Resolution Images Only

arXiv: https://arxiv.org/abs/2503.23265 · HTML: https://mlsanity.com/paper/2503.23265/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 30 Mar 2025.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [Dual Aggregation Transformer for Image Super-Resolution](https://mlsanity.com/paper/2308.03364/) (2023)
- [Meta-Transfer Learning for Zero-Shot Super-Resolution](https://mlsanity.com/paper/2002.12213/) (2020)
- [Cross Aggregation Transformer for Image Restoration](https://mlsanity.com/paper/2211.13654/) (2022)
- [Accurate Image Restoration with Attention Retractable Transformer](https://mlsanity.com/paper/2210.01427/) (2022)
- [SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2208.11247/) (2022)
- [Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy](https://mlsanity.com/paper/2004.00448/) (2020)
- [DRCT: Saving Image Super-resolution away from Information Bottleneck](https://mlsanity.com/paper/2404.00722/) (2024)
- [SimUSR: A Simple but Strong Baseline for Unsupervised Image Super-resolution](https://mlsanity.com/paper/2004.11020/) (2020)
- [ICF-SRSR: Invertible scale-Conditional Function for Self-Supervised Real-world Single Image Super-Resolution](https://mlsanity.com/paper/2307.12751/) (2023)

## Abstract (arXiv)

Transformer architectures prominently lead single-image super-resolution (SISR) benchmarks, reconstructing high-resolution (HR) images from their low-resolution (LR) counterparts. Their strong representative power, however, comes with a higher demand for training data compared to convolutional neural networks (CNNs). For many real-world SR applications, the availability of high-quality HR training images is not given, sparking interest in LR-only training methods. The LR-only SISR benchmark mimics this condition by allowing only low-resolution (LR) images for model training. For a 4x super-resolution, this effectively reduces the amount of available training data to 6.25% of the HR image pixels, which puts the employment of a data-hungry transformer model into question. In this work, we are the first to utilize a lightweight vision transformer model with LR-only training methods addressing the unsupervised SISR LR-only benchmark. We adopt and configure a recent LR-only training method from microscopy image super-resolution to macroscopic real-world data, resulting in our multi-scale training method for bicubic degradation (MSTbic). Furthermore, we compare it with reference methods and prove its effectiveness both for a transformer and a CNN model. We evaluate on the classic SR benchmark datasets Set5, Set14, BSD100, Urban100, and Manga109, and show superior performance over state-of-the-art (so far: CNN-based) LR-only SISR methods. The code is available on GitHub: https://github.com/ifnspaml/SuperResolutionMultiscaleTraining.