Perceptual Loss based Approach for Analogue Film Restoration

Daniela Ivanova, Jan Paul Siebert, John Williamson

2022

Abstract

Analogue film restoration, both for still photographs and motion picture emulsions, is a slow and laborious manual process. Artifacts such as dust and scratches are random in shape, size, and location; additionally, the overall degree of damage varies between different frames. We address this less popular case of image restoration by training a U-Net model with a modified perceptual loss function. Along with the novel perceptual loss function used for training, we propose a more rigorous quantitative model evaluation approach which measures the overall degree of improvement in perceptual quality over our test set.

Paper Citation

in Harvard Style

Ivanova D., Siebert J. and Williamson J. (2022). Perceptual Loss based Approach for Analogue Film Restoration. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 126-135. DOI: 10.5220/0010829300003124

in Bibtex Style

@conference{visapp22,
author={Daniela Ivanova and Jan Paul Siebert and John Williamson},
title={Perceptual Loss based Approach for Analogue Film Restoration},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={126-135},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010829300003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Perceptual Loss based Approach for Analogue Film Restoration
SN - 978-989-758-555-5
AU - Ivanova D.
AU - Siebert J.
AU - Williamson J.
PY - 2022
SP - 126
EP - 135
DO - 10.5220/0010829300003124
PB - SciTePress