Recovering High Intensity Images from Sequential Low Light Images

Masahiro Hayashi, Fumihiko Sakaue, Jun Sato, Yoshiteru Koreeda, Masakatsu Higashikubo, Hidenori Yamamoto

2022

Abstract

In this paper, we propose a method for recovering high intensity images from degraded low intensity images taken in low light. In particular, we show that by using the sequence of low light images, the high intensity image can be generated more accurately. For using the sequence of images, we have to deal with moving objects in the image. We combine multiple networks for generating accurate high intensity images in the presence of moving objects. We also introduce newly defined loss called character recognition loss for obtaining more accurate high intensity images.

Paper Citation

in Harvard Style

Hayashi M., Sakaue F., Sato J., Koreeda Y., Higashikubo M. and Yamamoto H. (2022). Recovering High Intensity Images from Sequential Low Light Images. 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 599-606. DOI: 10.5220/0010891600003124

in Bibtex Style

@conference{visapp22,
author={Masahiro Hayashi and Fumihiko Sakaue and Jun Sato and Yoshiteru Koreeda and Masakatsu Higashikubo and Hidenori Yamamoto},
title={Recovering High Intensity Images from Sequential Low Light Images},
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={599-606},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010891600003124},
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 - Recovering High Intensity Images from Sequential Low Light Images
SN - 978-989-758-555-5
AU - Hayashi M.
AU - Sakaue F.
AU - Sato J.
AU - Koreeda Y.
AU - Higashikubo M.
AU - Yamamoto H.
PY - 2022
SP - 599
EP - 606
DO - 10.5220/0010891600003124
PB - SciTePress