Binocular Rivalry Oriented Predictive Autoencoding Network for Blind Stereoscopic Image Quality Measurement

Abstract

Stereoscopic image quality measurement (SIQM) has become increasingly important for guiding stereo image processing and commutation systems due to the widespread usage of 3-D contents. Compared with conventional methods that are relied on handcrafted features, deep-learning-oriented measurements have achieved remarkable performance in recent years. However, most existing deep SIQM evaluators are not specifically built for stereoscopic contents and consider little prior domain knowledge of the 3-D human visual system (HVS) in network design. In this article, we develop a Predictive Auto-encoDing Network (PAD-Net) for blind/no-reference SIQM. In the first stage, inspired by the predictive coding theory that the cognition system tries to match bottom-up visual signal with top-down predictions, we adopt the encoder-decoder architecture to reconstruct the distorted inputs. Besides, motivated by the binocular rivalry phenomenon, we leverage the likelihood and prior maps generated from the predictive coding process in the Siamese framework for assisting SIQM. In the second stage, a quality regression network is applied to the fusion image for acquiring the perceptual quality prediction. The performance of PAD-Net has been extensively evaluated on three benchmark databases and the superiority has been well validated on both symmetrically and asymmetrically distorted stereoscopic images under various distortion types.