Uncertainty Estimation for Super-Resolution Using ESRGAN

Maniraj Sai Adapa, Marco Zullich, Matias Valdenegro-Toro

2025

Abstract

Deep Learning-based image super-resolution (SR) has been gaining traction with the aid of Generative Adversarial Networks. Models like SRGAN and ESRGAN are constantly ranked between the best image SR tools. However, they lack principled ways for estimating predictive uncertainty. In the present work, we enhance these models using Monte Carlo-Dropout and Deep Ensemble, allowing the computation of predictive uncertainty. When coupled with a prediction, uncertainty estimates can provide more information to the model users, highlighting pixels where the SR output might be uncertain, hence potentially inaccurate, if these estimates were to be reliable. Our findings suggest that these uncertainty estimates are decently calibrated and can hence fulfill this goal, while providing no performance drop with respect to the corresponding models without uncertainty estimation.

Paper Citation

in Harvard Style

Adapa M., Zullich M. and Valdenegro-Toro M. (2025). Uncertainty Estimation for Super-Resolution Using ESRGAN. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 367-374. DOI: 10.5220/0013150700003912

in Bibtex Style

@conference{visapp25,
author={Maniraj Adapa and Marco Zullich and Matias Valdenegro-Toro},
title={Uncertainty Estimation for Super-Resolution Using ESRGAN},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={367-374},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013150700003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Uncertainty Estimation for Super-Resolution Using ESRGAN
SN - 978-989-758-728-3
AU - Adapa M.
AU - Zullich M.
AU - Valdenegro-Toro M.
PY - 2025
SP - 367
EP - 374
DO - 10.5220/0013150700003912
PB - SciTePress