Full-reference quality assessment of stereopairs accounting for rivalry

• A 3D QA framework that models binocular rivalry is proposed.
• The proposed framework significantly improves the performance of 2D QA models in predicting 3D quality of stereoscopic 3D images.
• A 3D image quality database with ground truth disparity is constructed and will be made public.

We develop a framework for assessing the quality of stereoscopic images that have been afflicted by possibly asymmetric distortions. An intermediate image is generated which when viewed stereoscopically is designed to have a perceived quality close to that of the cyclopean image. We hypothesize that performing stereoscopic QA on the intermediate image yields higher correlations with human subjective judgments. The experimental results confirm the hypothesis and show that the proposed framework significantly outperforms conventional 2D QA metrics when predicting the quality of stereoscopically viewed images that may have been asymmetrically distorted.