Predicting Stereoscopic Image Quality via Stacked Auto-Encoders Based on Stereopsis Formation

Abstract

Most previous 2-D and 3-D image quality evaluators were based on shallow architectures. Their shallow architectures cannot model phenomenon occurring in human visual systems sufficiently. Disparities between left and right views have been importantly used for 3-D image quality assessment (IQA), but single disparity, depth, or cyclopean maps made from the disparities cannot thoroughly reflect the depth sense. In this paper, we propose a blind stereoscopic image quality evaluator using stacked auto-encoders (SAE). The proposed method is based on two theories on initial stages of stereopsis. One is cyclopean channel theory and the other is binocular summation/difference channels theory. Especially, a cyclopean image that models the former theory is computed to consider binocular suppression, whereas summation and difference images that model the latter one are utilized to treat the depth sense. We train three SAEs for quality-aware features from the three images in an unsupervised manner. Through the SAEs, the features are transformed into more meaningful features, and they are used to train two regressors. The regressors are used to obtain a final predicted score. Experimental results conducted on popular 3-D IQA databases prove that the proposed algorithm outperforms state-of-the-art 3-D IQA methods.