No-reference Image Quality Assessment via Non-local Dependency Modeling

In this paper, we propose a no-reference image quality assessment method based on non-local features learned by a graph neural network (GNN). The proposed quality assessment framework is rooted in the view that the human visual system perceives image quality with long-dependency constructed among different regions, inspiring us to explore the non-local interactions in quality prediction. Instead of relying on convolutional neural network (CNN) based quality assessment methods that primarily focus on local field features, the GNN aiming for non-local quality perception facilitates modeling such long-dependency. In particular, we first adopt superpixel segmentation for the graph nodes construction. Subsequently, a spatial attention module is proposed to integrate the long- and short-range dependencies among the nodes of the whole image. The learned non-local features are finally combined with the local features extracted by the pre-trained CNN, achieving superior performance to the features utilized individually. Experimental results on intra-dataset and cross-dataset settings verify our proposed method's effectiveness and advanced generalization capability. Source codes are publicly accessible at https://github.com/SuperBruceJia/NLNet-IQA for scientific reproducible research.