A Study in Dataset Distillation for Image Super-Resolution
Feb 5, 2025·,
Tobias Christian Nauen,,,
Tobias Dietz
Brian Bernhard Moser
Tobias Christian NauenFederico Raue
Stanislav Frolov
Andreas Dengel
Abstract
Dataset distillation aims to compress large datasets into compact yet highly informative subsets that preserve the training behavior of the original data. While this concept has gained traction in classification, its potential for image Super-Resolution (SR) remains largely untapped. In this work, we conduct the first systematic study of dataset distillation for SR, evaluating both pixel- and latent-space formulations. We show that a distilled dataset, occupying only 8.88% of the original size, can train SR models that retain nearly the same reconstruction fidelity as those trained on full datasets. Furthermore, we analyze how initialization strategies and distillation objectives affect efficiency, convergence, and visual quality. Our findings highlight the feasibility of SR dataset distillation and establish foundational insights for memory- and compute-efficient generative restoration models.
Type
Publication
arXiv preprint
(arXiv)
Citation
If you use this work, please cite our paper:
@misc{dietz2025datadistillsr,
title={A Study in Dataset Distillation for Image Super-Resolution},
author={Tobias Dietz and Brian B. Moser and Tobias Nauen and Federico Raue and Stanislav Frolov and Andreas Dengel},
year={2025},
eprint={2502.03656},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2502.03656},
}
Authors
PhD Student
I’m a researcher of artificial intelligence at DFKI and RPTU Kaiserslautern-Landau.
My research interests include efficient deep learning, transformer models, multimodal learning, and computer vision.
In my PhD project, my focus lies on the development of efficient transformer models for vision, language, and multimodal tasks.