计算机科学
推论
人工智能
依赖关系(UML)
失真(音乐)
图像(数学)
图像质量
卷积神经网络
模式识别(心理学)
任务(项目管理)
生成语法
质量(理念)
机器学习
计算机网络
放大器
管理
带宽(计算)
经济
哲学
认识论
作者
Jupo Ma,Jinjian Wu,Leida Li,Weisheng Dong,Xuemei Xie
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2020-06-09
被引量:9
标识
DOI:10.1109/icme46284.2020.9102895
摘要
No-reference image quality assessment (NR-IQA) is a challenging task. It is a promising idea to design NR-IQA algorithms by mimicking how human visual system (HVS) works. The internal generative mechanism (IGM) indicates that HVS actively infers the primary content of an image for better understanding. Inspired by that, a novel NR-IQA method with active inference is proposed in this paper. First, a generative adversarial network (GAN) is proposed to predict the primary content of a distorted image, in which two IGM-inspired constraints are considered during the optimization. Next, based on the correlation between the distorted image and its primary content, different degradations (i.e., the content/distortion-/structure-dependency degradation) are measured simultaneously with a multi-stream convolutional neural network (CNN) for NR-IQA. Benefit from the primary content obtained from GAN and the multiple degradations measurement of CNN, our method achieves the state-of-the-art on five public IQA databases.
科研通智能强力驱动
Strongly Powered by AbleSci AI