Algorithmic assessment of 3D quality of experience for images and videos

We propose a no-reference algorithm to assess the comfort associated with viewing stereo images and videos. The proposed measure of 3D quality of experience is shown to correlate well with human perception of quality on a publicly available dataset of 3D images/videos and human subjective scores. The proposed measure extracts statistical features from disparity and disparity gradient maps as well as indicators of spatial activity from images. For videos, the measure utilizes these spatial features along with motion compensated disparity differences to predict quality of experience. To the best of our knowledge the proposed approach is the first attempt in algorithmically assessing the subjective quality of experience on a publicly available dataset.