A good distortion representation is crucial for the success of deep blind image quality assessment (BIQA). However, most previous methods do not effectively model the relationship between distortions or the distribution of samples with the same distortion type but different distortion levels. In this work, we start from the analysis of the relationship between perceptual image quality and distortion-related factors, such as distortion types and levels. Then, we propose a Distortion Graph Representation (DGR) learning framework for IQA, named GraphIQA, in which each distortion is represented as a graph, \ieno, DGR. One can distinguish distortion types by learning the contrast relationship between these different DGRs, and infer the ranking distribution of samples from different levels in a DGR. Specifically, we develop two sub-networks to learn the DGRs: a) Type Discrimination Network (TDN) that aims to embed DGR into a compact code for better discriminating distortion types and learning the relationship between types; b) Fuzzy Prediction Network (FPN) that aims to extract the distributional characteristics of the samples in a DGR and predicts fuzzy degrees based on a Gaussian prior. Experiments show that our GraphIQA achieves the state-of-the-art performance on many benchmark datasets of both synthetic and authentic distortions.

翻译：良好的扭曲代表性对于深视图像质量评估(BIQA)的成功至关重要。然而,大多数以往的方法并不能够有效地模拟扭曲或不同扭曲类型、但不同扭曲程度的样本分布之间的关系。在这项工作中,我们首先分析视觉图像质量与扭曲相关因素(如扭曲类型和级别)之间的关系。然后,我们提议为IQA(名为GapIQA)建立一个扭曲图代表学习框架,其中每个扭曲都以图表(\ieno,DGR)为代表。一个人可以通过了解不同DGR之间的对比关系来区分扭曲类型,并推断DGR不同级别样本的排名分布情况。具体地说,我们开发了两个子网络来学习DGR:a)类型歧视网络(TDN),目的是将DGR纳入一个契约代码,以更好地区分扭曲类型和学习类型之间的关系;b)模糊的预测网络(FPFN),目的是通过在DGR中提取样品的分布特征,并预测DGRRGR(根据我们之前的合成A数据分析结果和图像显示我们之前的精确度。