An Efficient Algorithm to Select Reference Views for Virtual View Synthesis
View synthesis is one of the key techniques for generating immersive media. Virtual view synthesis techniques require considerable input views to provide a wide viewing space to users, such as 360 virtual reality. However, the computational complexity is increased, and the synthesized virtual image...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9794691/ |
_version_ | 1828820542193401856 |
---|---|
author | Da-Yoon Nam Woo-Kyung Jung Hyeon-Deok Han Jong-Ki Han |
author_facet | Da-Yoon Nam Woo-Kyung Jung Hyeon-Deok Han Jong-Ki Han |
author_sort | Da-Yoon Nam |
collection | DOAJ |
description | View synthesis is one of the key techniques for generating immersive media. Virtual view synthesis techniques require considerable input views to provide a wide viewing space to users, such as 360 virtual reality. However, the computational complexity is increased, and the synthesized virtual image is blurred when all input views are used as reference views. We analyzed the algorithm complexity and synthesized image quality according to the number of reference pictures. Based on the results, we propose a systematic algorithm to compose an optimal subset of the reference pictures to reduce the hole area and increase the accuracy of the overlapped pixel data in the virtual view. The algorithm consists of the screening and optimal composing steps, which involve logical and geometric measurements. The experimental results demonstrate that the proposed method reduces algorithm complexity and improves the virtual view quality. |
first_indexed | 2024-12-12T12:35:59Z |
format | Article |
id | doaj.art-ef12822b130d4fe39709ad95cf123251 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-12-12T12:35:59Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-ef12822b130d4fe39709ad95cf1232512022-12-22T00:24:20ZengIEEEIEEE Access2169-35362022-01-0110623066232110.1109/ACCESS.2022.31824019794691An Efficient Algorithm to Select Reference Views for Virtual View SynthesisDa-Yoon Nam0Woo-Kyung Jung1Hyeon-Deok Han2https://orcid.org/0000-0001-6323-593XJong-Ki Han3https://orcid.org/0000-0002-5036-7199Department of Information and Communication Engineering, Sejong University, Gwangjin-gu, Seoul, South KoreaDepartment of Information and Communication Engineering, Sejong University, Gwangjin-gu, Seoul, South KoreaDepartment of Information and Communication Engineering, Sejong University, Gwangjin-gu, Seoul, South KoreaDepartment of Electrical Engineering, Sejong University, Gwangjin-gu, Seoul, South KoreaView synthesis is one of the key techniques for generating immersive media. Virtual view synthesis techniques require considerable input views to provide a wide viewing space to users, such as 360 virtual reality. However, the computational complexity is increased, and the synthesized virtual image is blurred when all input views are used as reference views. We analyzed the algorithm complexity and synthesized image quality according to the number of reference pictures. Based on the results, we propose a systematic algorithm to compose an optimal subset of the reference pictures to reduce the hole area and increase the accuracy of the overlapped pixel data in the virtual view. The algorithm consists of the screening and optimal composing steps, which involve logical and geometric measurements. The experimental results demonstrate that the proposed method reduces algorithm complexity and improves the virtual view quality.https://ieeexplore.ieee.org/document/9794691/Immersive imagereference view selectionvirtual view synthesis |
spellingShingle | Da-Yoon Nam Woo-Kyung Jung Hyeon-Deok Han Jong-Ki Han An Efficient Algorithm to Select Reference Views for Virtual View Synthesis IEEE Access Immersive image reference view selection virtual view synthesis |
title | An Efficient Algorithm to Select Reference Views for Virtual View Synthesis |
title_full | An Efficient Algorithm to Select Reference Views for Virtual View Synthesis |
title_fullStr | An Efficient Algorithm to Select Reference Views for Virtual View Synthesis |
title_full_unstemmed | An Efficient Algorithm to Select Reference Views for Virtual View Synthesis |
title_short | An Efficient Algorithm to Select Reference Views for Virtual View Synthesis |
title_sort | efficient algorithm to select reference views for virtual view synthesis |
topic | Immersive image reference view selection virtual view synthesis |
url | https://ieeexplore.ieee.org/document/9794691/ |
work_keys_str_mv | AT dayoonnam anefficientalgorithmtoselectreferenceviewsforvirtualviewsynthesis AT wookyungjung anefficientalgorithmtoselectreferenceviewsforvirtualviewsynthesis AT hyeondeokhan anefficientalgorithmtoselectreferenceviewsforvirtualviewsynthesis AT jongkihan anefficientalgorithmtoselectreferenceviewsforvirtualviewsynthesis AT dayoonnam efficientalgorithmtoselectreferenceviewsforvirtualviewsynthesis AT wookyungjung efficientalgorithmtoselectreferenceviewsforvirtualviewsynthesis AT hyeondeokhan efficientalgorithmtoselectreferenceviewsforvirtualviewsynthesis AT jongkihan efficientalgorithmtoselectreferenceviewsforvirtualviewsynthesis |