Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Subjective quality assessment of stereoscopic omnidirectional image

Xu, Jiahua, Lin, Chaoyi, Zhou, Wei and Chen, Zhibo 2018. Subjective quality assessment of stereoscopic omnidirectional image. Presented at: 19th Pacific-Rim Conference on Multimedia, Hefei, China, 21-22 Sept 2018. Published in: Hong, Richard, Cheng, Wen-Huang, Yamasaki, Toshihiko, Wang, Meng and Ngo, Chong-Wah eds. Advances in Multimedia Information Processing – PCM 2018. Lecture Notes in Computer Science. Lecture Notes in Computer Science (11164) Springer, pp. 589-599. 10.1007/978-3-030-00776-8_54

Full text not available from this repository.


Stereoscopic omnidirectional images are eye-catching because they can provide realistic and immersive experience. Due to the extra depth perception provided by stereoscopic omnidirectional images, it is desirable and urgent to evaluate the overall quality of experience (QoE) of these images, including image quality, depth perception, and so on. However, most existing studies are based on 2D omnidirectional images and only image quality is taken into account. In this paper, we establish the very first Stereoscopic OmnidirectionaL Image quality assessment Database (SOLID). Three subjective evaluating factors are considered in our database, namely image quality, depth perception, and overall QoE. Additionally, the relationship among these three factors is investigated. Finally, several well-known image quality assessment (IQA) metrics are tested on our SOLID database. Experimental results demonstrate that the objective overall QoE assessment is more challenging compared to IQA in terms of stereoscopic omnidirectional images. We believe that our database and findings will provide useful insights in the development of the QoE assessment for stereoscopic omnidirectional images.

Item Type: Conference or Workshop Item (Paper)
Date Type: Published Online
Status: Published
Schools: Computer Science & Informatics
Publisher: Springer
ISBN: 978-3-030-00775-1
ISSN: 0302-9743
Last Modified: 24 Aug 2023 10:57

Actions (repository staff only)

Edit Item Edit Item