Hierarchical Graph Attention Network for No-Reference Omnidirectional Image Quality Assessment

TL;DR

This paper introduces a hierarchical graph attention network that models local and global spatial distortions in omnidirectional images for improved no-reference quality assessment, outperforming existing methods.

Contribution

It presents a novel graph neural network framework using Fibonacci sphere sampling, GAT, and graph transformer to better capture spatial distortion variations in OIQA.

Findings

Significantly outperforms existing OIQA methods on large-scale databases.

Effectively models local non-uniform distortions and long-range interactions.

Demonstrates strong generalization across diverse spatial distortions.

Abstract

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.