Towards Top-Down Stereo Image Quality Assessment via Stereo Attention

TL;DR

This paper introduces SATNet, a top-down stereo image quality assessment model that uses attention mechanisms and binocular response tuning to improve the accuracy of 3D content quality evaluation.

Contribution

The paper proposes a novel top-down stereo attention network with adaptive attention and energy coefficient mechanisms for enhanced SIQA performance.

Findings

Outperforms existing SIQA methods on benchmark datasets.

Effectively models human visual system characteristics in stereo quality assessment.

Demonstrates the importance of top-down attention in stereo image quality evaluation.

Abstract

Stereo image quality assessment (SIQA) plays a crucial role in evaluating and improving the visual experience of 3D content. Existing visual properties-based methods for SIQA have achieved promising performance. However, these approaches ignore the top-down philosophy, leading to a lack of a comprehensive grasp of the human visual system (HVS) and SIQA. This paper presents a novel Stereo AttenTion Network (SATNet), which employs a top-down perspective to guide the quality assessment process. Specifically, our generalized Stereo AttenTion (SAT) structure adapts components and input/output for stereo scenarios. It leverages the fusion-generated attention map as a higher-level binocular modulator to influence two lower-level monocular features, allowing progressive recalibration of both throughout the pipeline. Additionally, we introduce an Energy Coefficient (EC) to flexibly tune the magnitude of binocular response, accounting for the fact that binocular responses in the primate primary visual cortex are less than the sum of monocular responses. To extract the most discriminative quality information from the summation and subtraction of the two branches of monocular features, we utilize a dual-pooling strategy that applies min-pooling and max-pooling operations to the respective branches. Experimental results highlight the superiority of our top-down method in advancing the state-of-the-art in the SIQA field. The code is available at https://github.com/Fanning-Zhang/SATNet.