In this paper, we propose a depth map quality metric for three-dimensional videos which include stereoscopic videos andautostereoscopic videos. Recently, a number of researches have been done to figure out the relationship of perceptualquality and video impairment caused by various compression methods. However, we consider non-compression issueswhich are induced during acquisition and displaying. For instance, using multiple cameras structure may causeimpairment such as misalignment. We demonstrate that the depth map can be a useful tool to find out the impliedimpairments. The proposed quality metrics using depth map are depth range, vertical misalignment, temporalconsistency. The depth map is acquired by solving corresponding problems from stereoscopic video, widely known asdisparity estimation. After disparity estimation, the proposed metrics are calculated and integrated into one value whichindicates estimated visual fatigue based on the results of subjective assessment. We measure the correlation betweenobjective quality metrics and subjective quality results to validate our metrics.
展开▼
