用图神经网络分析全景图像局部失真，提升无参考质量评估精度
Hierarchical Graph Attention Network for No-Reference Omnidirectional Image Quality Assessment
- 基于斐波那契球采样生成视口图，构建空间拓扑关系图
- 融合图注意力与图变换器，捕捉局部细节与远程质量关联
- 在两个大规模数据集上超越现有方法，适合全景图像质量评估场景
当前全景图像质量评估（OIQA）方法难以有效建模局部非均匀失真，主要因对空间质量变化的表征不足。为此，本文提出基于图神经网络的OIQA框架，显式建模视口间的结构关系以增强对空间失真非均匀性的感知。通过斐波那契球采样生成具有良好拓扑结构的视口，每个视口作为图节点，经多阶段特征提取网络获得高维表示。为全面捕捉空间依赖性，集成图注意力网络（GAT）以建模相邻视口间的细粒度局部失真变化，并引入图变压器捕捉远距离区域间的长程质量交互。在包含复杂空间失真的两个大规模OIQA数据库上的大量实验表明，本方法显著优于现有方法，验证了其有效性与强泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。