Towards Top-Down Stereo Image Quality Assessment via Stereo Attention
This work addresses the problem of evaluating 3D content quality for applications in multimedia and vision systems, representing an incremental improvement over existing methods.
The paper tackles stereo image quality assessment (SIQA) by proposing a top-down Stereo AttenTion Network (SATNet) that uses attention maps and an energy coefficient to model human visual system principles, achieving state-of-the-art performance in the field.
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.