Haze Relevant Feature Attention Network for Single Image Dehazing

doi:10.1109/ACCESS.2021.3100604

CIOMP OpenIR

	Haze Relevant Feature Attention Network for Single Image Dehazing
	X. Jiang; L. Lu; M. Zhu; Z. Hao and W. Gao
	2021
发表期刊	IEEE Access
ISSN	21693536
卷号	9 页码:106476-106488
摘要	Single image dehazing methods based on deep learning technique have made great achievements in recent years. However, some methods recover haze-free images by estimating the so-called transmission map and global atmospheric light, which are strictly limited to the simplified atmospheric scattering model and do not give full play to the advantages of deep learning to fit complex functions. Other methods require pairs of training data, whereas in practice pairs of hazy and corresponding haze-free images are difficult to obtain. To address these problems, inspired by cycle generative adversarial model, we have developed an end-To-end haze relevant feature attention network for single image dehazing, which does not require paired training images. Specifically, we make explicit use of haze relevant feature by embedding an attention module into a novel dehazing generator that combines an encoder-decoder structure with dense blocks. The constructed network adopts a novel strategy which derives attention maps from several hand-designed priors, such as dark channel, color attenuation, maximum contrast and so on. Since haze is usually unevenly distributed across an image, the attention maps could serve as a guidance of the amount of haze at image pixels. Meanwhile, dense blocks can maximize information flow along features from different levels. Furthermore, color loss is proposed to avoid color distortion and generate visually better haze-free images. Extensive experiments demonstrate that the proposed method achieves significant improvements over the state-of-The-Art methods. 2013 IEEE.
DOI	10.1109/ACCESS.2021.3100604
URL	查看原文
收录类别	SCI ; EI
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/65281
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	X. Jiang,L. Lu,M. Zhu,et al. Haze Relevant Feature Attention Network for Single Image Dehazing[J]. IEEE Access,2021,9:106476-106488.
APA	X. Jiang,L. Lu,M. Zhu,&Z. Hao and W. Gao.(2021).Haze Relevant Feature Attention Network for Single Image Dehazing.IEEE Access,9,106476-106488.
MLA	X. Jiang,et al."Haze Relevant Feature Attention Network for Single Image Dehazing".IEEE Access 9(2021):106476-106488.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Haze Relevant Featur（6612KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载