The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
사용자에게 몰입형 경험을 제공하는 능력 덕분에 최근 몇 년 동안 가상 현실(VR) 기술이 인기를 얻고 있습니다. VR 시스템의 핵심 구성 요소는 장면을 360도 뷰로 제공할 수 있는 전방향 콘텐츠입니다. 그러나 주어진 시간에 전체 전방향 콘텐츠 중 일부만 뷰포트, 은 사용자의 현재 보는 방향에 따라 표시됩니다. 이 작업에서 우리는 먼저 개발합니다. W-VPSNR(가중 뷰포트 PSNR), 전방향 콘텐츠의 품질 평가를 위한 객관적인 품질 측정 기준입니다. 제안된 측정기준은 인간 시각 시스템의 중심(foveation) 특징을 고려합니다. 그런 다음 공간적으로 다양한 뷰포트 품질을 갖는 72개의 자극으로 구성된 주관적 데이터베이스를 구축합니다. 이 데이터베이스를 이용하여 제안된 지표와 XNUMX가지 기존 지표에 대한 평가를 수행한다. 실험 결과는 W-VPSNR 메트릭이 평균 의견 점수(MOS)와 잘 연관되어 있으며 기존 메트릭보다 성능이 우수하다는 것을 보여줍니다. 또한, 기존의 메트릭은 전방향 콘텐츠에 대해서는 잘 수행되지 않는 것으로 나타났습니다.
Huyen T. T. TRAN
University of Aizu
Trang H. HOANG
Hanoi University of Science and Technology
Phu N. MINH
Hanoi University of Science and Technology
Nam PHAM NGOC
Vin-University project
Truong CONG THANG
University of Aizu
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Huyen T. T. TRAN, Trang H. HOANG, Phu N. MINH, Nam PHAM NGOC, Truong CONG THANG, "A Weighted Viewport Quality Metric for Omnidirectional Images" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 1, pp. 67-70, January 2020, doi: 10.1587/transinf.2019MUL0002.
Abstract: Thanks to the ability to bring immersive experiences to users, Virtual Reality (VR) technologies have been gaining popularity in recent years. A key component in VR systems is omnidirectional content, which can provide 360-degree views of scenes. However, at a given time, only a portion of the full omnidirectional content, called viewport, is displayed corresponding to the user's current viewing direction. In this work, we first develop Weighted-Viewport PSNR (W-VPSNR), an objective quality metric for quality assessment of omnidirectional content. The proposed metric takes into account the foveation feature of the human visual system. Then, we build a subjective database consisting of 72 stimuli with spatial varying viewport quality. By using this database, an evaluation of the proposed metric and four conventional metrics is conducted. Experiment results show that the W-VPSNR metric well correlates with the mean opinion scores (MOS) and outperforms the conventional metrics. Also, it is found that the conventional metrics do not perform well for omnidirectional content.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019MUL0002/_p
부
@ARTICLE{e103-d_1_67,
author={Huyen T. T. TRAN, Trang H. HOANG, Phu N. MINH, Nam PHAM NGOC, Truong CONG THANG, },
journal={IEICE TRANSACTIONS on Information},
title={A Weighted Viewport Quality Metric for Omnidirectional Images},
year={2020},
volume={E103-D},
number={1},
pages={67-70},
abstract={Thanks to the ability to bring immersive experiences to users, Virtual Reality (VR) technologies have been gaining popularity in recent years. A key component in VR systems is omnidirectional content, which can provide 360-degree views of scenes. However, at a given time, only a portion of the full omnidirectional content, called viewport, is displayed corresponding to the user's current viewing direction. In this work, we first develop Weighted-Viewport PSNR (W-VPSNR), an objective quality metric for quality assessment of omnidirectional content. The proposed metric takes into account the foveation feature of the human visual system. Then, we build a subjective database consisting of 72 stimuli with spatial varying viewport quality. By using this database, an evaluation of the proposed metric and four conventional metrics is conducted. Experiment results show that the W-VPSNR metric well correlates with the mean opinion scores (MOS) and outperforms the conventional metrics. Also, it is found that the conventional metrics do not perform well for omnidirectional content.},
keywords={},
doi={10.1587/transinf.2019MUL0002},
ISSN={1745-1361},
month={January},}
부
TY - JOUR
TI - A Weighted Viewport Quality Metric for Omnidirectional Images
T2 - IEICE TRANSACTIONS on Information
SP - 67
EP - 70
AU - Huyen T. T. TRAN
AU - Trang H. HOANG
AU - Phu N. MINH
AU - Nam PHAM NGOC
AU - Truong CONG THANG
PY - 2020
DO - 10.1587/transinf.2019MUL0002
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2020
AB - Thanks to the ability to bring immersive experiences to users, Virtual Reality (VR) technologies have been gaining popularity in recent years. A key component in VR systems is omnidirectional content, which can provide 360-degree views of scenes. However, at a given time, only a portion of the full omnidirectional content, called viewport, is displayed corresponding to the user's current viewing direction. In this work, we first develop Weighted-Viewport PSNR (W-VPSNR), an objective quality metric for quality assessment of omnidirectional content. The proposed metric takes into account the foveation feature of the human visual system. Then, we build a subjective database consisting of 72 stimuli with spatial varying viewport quality. By using this database, an evaluation of the proposed metric and four conventional metrics is conducted. Experiment results show that the W-VPSNR metric well correlates with the mean opinion scores (MOS) and outperforms the conventional metrics. Also, it is found that the conventional metrics do not perform well for omnidirectional content.
ER -