Generative adversarial dehaze mapping nets

doi:10.1016/j.patrec.2017.11.021

CORC > 兰州理工大学 > 兰州理工大学

	Generative adversarial dehaze mapping nets
	Li, Ce 1; Zhao, Xinyu 1; Zhang, Zhaoxiang 2; Du, Shaoyi 3
刊名	Pattern Recognition Letters
	2019-03-01
卷号	119 页码:238-244
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
ISSN号	01678655
DOI	10.1016/j.patrec.2017.11.021
英文摘要	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.
WOS研究方向	Computer Science
语种	英语
出版者	Elsevier B.V.
WOS记录号	WOS:000458876700029
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/150595]
专题	兰州理工大学
作者单位	1.Lanzhou University of Technology, Lanzhou; Gansu, China; 2.Chinese Academy of Sciences, Beijing, China; 3.Xi'an Jiaotong University, Xi'an; Shanxi, China
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.