Generative adversarial dehaze mapping nets

doi:10.1016/j.patrec.2017.11.021

	Generative adversarial dehaze mapping nets
	Li, Ce 1; Zhao, Xinyu 1; Zhang, Zhaoxiang 2; Du, Shaoyi 3
	2019-03-01
发表期刊	Pattern Recognition Letters
ISSN	01678655
卷号	119 页码:238-244
摘要	Single image haze removal is a challenging task with few effective constraints, which seriously affect performance of machine learning algorithms. In this paper, we propose a Generative Adversarial Dehaze Mapping Nets (GADMN) to estimate a medium transmission for an input hazy image. GADMN adopts Generative Adversarial Nets (GAN) based deep architecture, which maps haze-relevant features to medium transmission and uses the network to carry on the feedback restrain. We also propose a multiple-light scattering model, which adds artificial light source and diffuses reflection light emerged from reflected light in the mist. Since the interference light is estimated in this model, we name it Local Multi-scale Hierarchical Prediction Method (LMHPM), which is beneficial to recover the large luminance range image. Experimental result demonstrates that the proposed algorithm outperforms state-of-the-art methods, and exhibits better robustness and adaptability. © 2017 Elsevier B.V.
关键词	Learning algorithms Light sources Machine learning Mapping Artificial light source Deep architectures Effective constraints GADMN LMHPM Multiple light scattering Relevant features State-of-the-art methods
DOI	10.1016/j.patrec.2017.11.021
收录类别	EI ; SCIE
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000458876700029
出版者	Elsevier B.V.
EI入藏号	20181404968881
EI主题词	Light scattering
EI分类号	405.3 Surveying ; 741.1 Light/Optics
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/150595
专题	兰州理工大学
通讯作者	Li, Ce
作者单位	1.Lanzhou Univ Technol, Lanzhou, Gansu, Peoples R China; 2.Chinese Acad Sci, Beijing, Peoples R China; 3.Xi An Jiao Tong Univ, Xian, Shaanxi, Peoples R China
第一作者单位	兰州理工大学
通讯作者单位	兰州理工大学
第一作者的第一单位	兰州理工大学
推荐引用方式 GB/T 7714	Li, Ce,Zhao, Xinyu,Zhang, Zhaoxiang,et al. Generative adversarial dehaze mapping nets[J]. Pattern Recognition Letters,2019,119:238-244.
APA	Li, Ce,Zhao, Xinyu,Zhang, Zhaoxiang,&Du, Shaoyi.(2019).Generative adversarial dehaze mapping nets.Pattern Recognition Letters,119,238-244.
MLA	Li, Ce,et al."Generative adversarial dehaze mapping nets".Pattern Recognition Letters 119(2019):238-244.