Blind Stereo Image Quality Assessment Inspired by Brain Sensory-Motor Fusion

TL;DR

This paper introduces a brain-inspired stereo image quality assessment method that fuses images, synthesizes views, extracts features based on distortion effects, and employs a neural network to evaluate 3D image quality more accurately.

Contribution

It proposes a novel brain-inspired fusion and synthesis approach combined with neural networks for improved stereo image quality assessment.

Findings

Outperforms existing stereo image quality metrics

Effectively detects various distortion types and severities

Validated on popular 3D image databases

Abstract

The use of 3D and stereo imaging is rapidly increasing. Compression, transmission, and processing could degrade the quality of stereo images. Quality assessment of such images is different than their 2D counterparts. Metrics that represent 3D perception by human visual system (HVS) are expected to assess stereoscopic quality more accurately. In this paper, inspired by brain sensory/motor fusion process, two stereo images are fused together. Then from every fused image two synthesized images are extracted. Effects of different distortions on statistical distributions of the synthesized images are shown. Based on the observed statistical changes, features are extracted from these synthesized images. These features can reveal type and severity of distortions. Then, a stacked neural network model is proposed, which learns the extracted features and accurately evaluates the quality of stereo images. This model is tested on 3D images of popular databases. Experimental results show the superiority of this method over state of the art stereo image quality assessment approaches