DEEP LEARNING AND CYCLOPEAN VIEW FOR NO-REFERENCE STEREOSCOPIC IMAGE QUALITY ASSESSMENT

This paper mainly introduces a new referenceless stereo-pair quality assessment using cyclopean view and deep learning. The proposed method is based on Human Visual System (HVS) modeling. Firstly, the cyclopean image is constructed considering the presence of binocular rivalry/suppression in order to cover the asymmetric distortion case. Secondly, the cyclopean image is divided into four patches, and we train four Convolutional Neural Network (CNN) prediction models. Finally, the trained models predict quality scores from the cyclopean image patches, and we average the scores to get the final quality assessment. The benchmark 3D LIVE phase I and 3D LIVE phase II databases have been used to evaluate the performance of our approach. Compared to the state-of-the-art full reference and no-reference stereoscopic image quality assessment metrics. The approach has shown competitive results and achieves consistent evaluation performance.