# Rethinking Image Super-Resolution from Training Data Perspectives

arXiv: https://arxiv.org/abs/2409.00768 · HTML: https://mlsanity.com/paper/2409.00768/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 1 Sep 2024.

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

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [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)
- [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)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019)
- [Efficient Long-Range Attention Network for Image Super-resolution](https://mlsanity.com/paper/2203.06697/) (2022)
- [Cross-Scale Internal Graph Neural Network for Image Super-Resolution](https://mlsanity.com/paper/2006.16673/) (2020)
- [SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2208.11247/) (2022)
- [On Efficient Transformer-Based Image Pre-training for Low-Level Vision](https://mlsanity.com/paper/2112.10175/) (2021)
- [PASS: An ImageNet replacement for self-supervised pretraining without humans](https://mlsanity.com/paper/2109.13228/) (2021)
- [Revisiting RCAN: Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2201.11279/) (2022)
- [HQ-50K: A Large-scale, High-quality Dataset for Image Restoration](https://mlsanity.com/paper/2306.05390/) (2023)

## Built on by (most cited first, 6 of 6)

- [Emulating Self-attention with Convolution for Efficient Image Super-Resolution](https://mlsanity.com/paper/2503.06671/) (2025)
- [LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Models](https://mlsanity.com/paper/2502.03950/) (2025)
- [Instance Data Condensation for Image Super-Resolution](https://mlsanity.com/paper/2505.21099/) (2025)
- [Rank-Factorized Implicit Neural Bias: Scaling Super-Resolution Transformer with FlashAttention](https://mlsanity.com/paper/2603.06738/) (2026)
- [4KLSDB: A Large-Scale Dataset for 4K Image Restoration and Generation](https://mlsanity.com/paper/2605.24762/) (2026)
- [CAT-Flow: Curvature-Adaptive sTeps for Flow Matching](https://mlsanity.com/paper/2609.01746/) (2026)

## Abstract (arXiv)

In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on common training datasets such as DIV2K and DF2K. However, we investigate and rethink the training data from the perspectives of diversity and quality, {thereby addressing the question of ``How important is SR training for SR models?''}. To this end, we propose an automated image evaluation pipeline. With this, we stratify existing high-resolution image datasets and larger-scale image datasets such as ImageNet and PASS to compare their performances. We find that datasets with (i) low compression artifacts, (ii) high within-image diversity as judged by the number of different objects, and (iii) a large number of images from ImageNet or PASS all positively affect SR performance. We hope that the proposed simple-yet-effective dataset curation pipeline will inform the construction of SR datasets in the future and yield overall better models.