Image-quality Improvement of Omnidirectional Free-viewpoint Images by Generative Adversarial Networks

Oto Takeuchi, Hidehiko Shishido, Yoshinari Kameda, Hansung Kim, Itaru Kitahara

2020

Abstract

This paper proposes a method to improve the quality of omnidirectional free-viewpoint images using generative adversarial networks (GAN). By estimating the 3D information of the capturing space while integrating the omnidirectional images taken from multiple viewpoints, it is possible to generate an arbitrary omnidirectional appearance. However, the image quality of free-viewpoint images deteriorates due to artifacts caused by 3D estimation errors and occlusion. We solve this problem by using GAN and, moreover, by focusing on projective geometry during training, we further improve image quality by converting the omnidirectional image into perspective-projection images.

Paper Citation

in Harvard Style

Takeuchi O., Shishido H., Kameda Y., Kim H. and Kitahara I. (2020). Image-quality Improvement of Omnidirectional Free-viewpoint Images by Generative Adversarial Networks. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 299-306. DOI: 10.5220/0008959802990306

in Bibtex Style

@conference{visapp20,
author={Oto Takeuchi and Hidehiko Shishido and Yoshinari Kameda and Hansung Kim and Itaru Kitahara},
title={Image-quality Improvement of Omnidirectional Free-viewpoint Images by Generative Adversarial Networks},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={299-306},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008959802990306},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP
TI - Image-quality Improvement of Omnidirectional Free-viewpoint Images by Generative Adversarial Networks
SN - 978-989-758-402-2
AU - Takeuchi O.
AU - Shishido H.
AU - Kameda Y.
AU - Kim H.
AU - Kitahara I.
PY - 2020
SP - 299
EP - 306
DO - 10.5220/0008959802990306
PB - SciTePress