Hierarchical Graph Attention Network for No-Reference Omnidirectional Image Quality Assessment
This work addresses the challenge of accurate quality assessment for omnidirectional images, which is crucial for applications like virtual reality, but it is incremental as it builds on existing graph-based and attention mechanisms.
The paper tackled the problem of evaluating locally non-uniform distortions in omnidirectional images by proposing a graph neural network framework that models structural relationships between viewports, achieving significant performance improvements over existing methods on two large-scale databases.
Current Omnidirectional Image Quality Assessment (OIQA) methods struggle to evaluate locally non-uniform distortions due to inadequate modeling of spatial variations in quality and ineffective feature representation capturing both local details and global context. To address this, we propose a graph neural network-based OIQA framework that explicitly models structural relationships between viewports to enhance perception of spatial distortion non-uniformity. Our approach employs Fibonacci sphere sampling to generate viewports with well-structured topology, representing each as a graph node. Multi-stage feature extraction networks then derive high-dimensional node representation. To holistically capture spatial dependencies, we integrate a Graph Attention Network (GAT) modeling fine-grained local distortion variations among adjacent viewports, and a graph transformer capturing long-range quality interactions across distant regions. Extensive experiments on two large-scale OIQA databases with complex spatial distortions demonstrate that our method significantly outperforms existing approaches, confirming its effectiveness and strong generalization capability.