Image-quality improvement of omnidirectional free-viewpoint images by generative adversarial networks
Image-quality improvement of omnidirectional free-viewpoint images by generative adversarial networks
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.
Computer graphics, Computer vision, Estimation errors, Free viewpoint images, Image quality improvements, Image quality, Adversarial networks, Multiple viewpoints, Omnidirectional image, Perspective projections, Projective geometry, Image enhancement
299-306
Takeuchi, O.
408f5f16-7a55-4a3e-bd8d-b2aee4a8a88e
Shishido, H.
266c89c3-848b-4efc-98c5-e1a4dc167fc7
Kameda, Y.
4fa1efaf-6c62-43eb-8167-4a6bf1d4a577
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Kitahara, I.
13b48c1f-8b52-4b65-9f98-e00c2bee22df
2020
Takeuchi, O.
408f5f16-7a55-4a3e-bd8d-b2aee4a8a88e
Shishido, H.
266c89c3-848b-4efc-98c5-e1a4dc167fc7
Kameda, Y.
4fa1efaf-6c62-43eb-8167-4a6bf1d4a577
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Kitahara, I.
13b48c1f-8b52-4b65-9f98-e00c2bee22df
Takeuchi, O., Shishido, H., Kameda, Y., Kim, H. and Kitahara, I.
(2020)
Image-quality improvement of omnidirectional free-viewpoint images by generative adversarial networks.
International Conference on Computer Vision Theory and Applications: VISAPP 2020, , Valetta, Malta.
27 - 29 Feb 2020.
.
Record type:
Conference or Workshop Item
(Paper)
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.
This record has no associated files available for download.
More information
Published date: 2020
Additional Information:
Funding Information:
This work was partially supported by JSPS KA-KENHI Grant Number 17H01772 and by JST CREST Grant Number JPMJCR14E2, Japan.
Publisher Copyright:
Copyright © 2020 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved
Venue - Dates:
International Conference on Computer Vision Theory and Applications: VISAPP 2020, , Valetta, Malta, 2020-02-27 - 2020-02-29
Keywords:
Computer graphics, Computer vision, Estimation errors, Free viewpoint images, Image quality improvements, Image quality, Adversarial networks, Multiple viewpoints, Omnidirectional image, Perspective projections, Projective geometry, Image enhancement
Identifiers
Local EPrints ID: 440628
URI: http://eprints.soton.ac.uk/id/eprint/440628
PURE UUID: f069c713-83ae-4b6d-b632-9602afd8d878
Catalogue record
Date deposited: 12 May 2020 16:46
Last modified: 23 Feb 2023 03:21
Export record
Contributors
Author:
O. Takeuchi
Author:
H. Shishido
Author:
Y. Kameda
Author:
H. Kim
Author:
I. Kitahara
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics