arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.07666cs.MM
收藏

GraphIQA:学习失真图表示用于盲图像质量评估

GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment

Simeng Sun, Tao Yu, Jiahua Xu, Wei Zhou, Zhibo Chen

AI总结:

本文提出GraphIQA框架,将每种失真表示为图(DGR),通过类型判别网络和模糊预测网络学习失真间关系及样本水平分布,在多个合成与真实失真基准上取得最优性能。

摘要:

良好的失真表示对于深度盲图像质量评估(BIQA)的成功至关重要。然而,大多数先前的方法未能有效建模失真之间的关系,或未能建模具有相同失真类型但不同失真水平的样本分布。在本工作中,我们从分析感知图像质量与失真相关因素(如失真类型和失真水平)之间的关系入手。然后,我们提出了一种用于IQA的失真图表示(DGR)学习框架,命名为GraphIQA,其中每种失真被表示为一个图,即DGR。通过学习这些不同DGR之间的对比关系,可以区分失真类型,并推断一个DGR中不同水平样本的排序分布。具体而言,我们开发了两个子网络来学习DGR:a) 类型判别网络(TDN),旨在将DGR嵌入为紧凑编码,以更好地判别失真类型并学习类型之间的关系;b) 模糊预测网络(FPN),旨在提取DGR中样本的分布特征,并基于高斯先验预测模糊度。实验表明,我们的GraphIQA在合成失真和真实失真的许多基准数据集上均取得了最先进的性能。

英文摘要:

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, i.e., 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑