On the Usefulness of Combined Metrics for 3D Image Quality Assessment

Abstract

Due to the growing popularity of 3D imaging technology which can be observed in recent years, one of the most relevant challenges for image quality assessment methods has become their extension towards reliable evaluation of stereoscopic images. Since known 2D image quality metrics are not necessarily well correlated with subjective quality scores of 3D images and the exact mechanism of the 3D quality perception is still unknown, there is a need of developing some new metrics better correlated with subjective perception of various distortions in 3D images. Since a promising direction of such research is related with the application of the combined metrics, the possibilities of their optimization for the 3D images are discussed in this paper together with experimental results obtained for the recently developed LIVE 3D Image Quality Database. © Springer International Publishing Switzerland 2015.