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.
Mohamed-Chaker Larabi, Audrey Girard, Sami Jaballah, Fan Yu, "Benchmark of 2D quality metrics for the assessment of 360-deg images" in Proc. IS&T 27th Color and Imaging Conf., 2019, pp 262 - 267, https://doi.org/10.2352/issn.2169-2629.2019.27.47