Depth map quality metric for three-dimensional video

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