Abstract
Omnidirectional or 360-degree images are becoming very popular in many applications and several challenges are raised because of both the nature and the representation of the data. Quality assessment is one of them from two different points of view: objectively or subjectively. In this paper, we propose to study the performance of different metrics belonging to various categories including simple mathematical metrics, humand perception based metrics and spherically optimized metrics. The performance of these metrics is measured using different tools such as PLCC, SROCC, KROCC and RMSE based on the only publically available database from Nanjing university. The results show that the metric that are considered as optimized for 360 degrees images are not providing the best correlation with the human judgement of the quality.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
