Multi-scale Densely Connected Dehazing Network

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	Multi-scale Densely Connected Dehazing Network
	Zhang Z(张箴)1,2,3; Tan JD(田建东)2,3; Cui T(崔童)1,2,3 ; Tang YD(唐延东)2,3
	2019
会议日期	August 8-11, 2019
会议地点	Shenyang, China
关键词	Deep learning image dehazing Multi-scale dense network One-in-all training Large-scale dataset
页码	594-604
英文摘要	Single image dehazing is a challenging ill-posed problem. The traditional methods mainly focus on estimating the transmission of atmospheric-light medium with some priors or constraints. In this paper, we propose a novel end-to-end convolutional neural network (CNN) for image dehazing, called multi-scale densely connected dehazing network (MDCDN). The proposed network consists of a parallel multi-scale densely connected CNN network and an encoder-decoder U net. The parallel multi-scale dense-net can estimate transmission map accurately. The encoder-decoder U net is used to estimate the atmospheric light intensity. The all-in-one training can jointly learn the transmission map, atmospheric light, and dehazing images all together with jointly MSE error and a discriminator loss. We also create a dataset with indoor and outdoor data based on the LFSD, NLPR, and NYU2 depth datasets to train our network. Extensive experiments demonstrate that, in most cases, the proposed method achieves significant improvements over the state-of-the-art methods.
产权排序	1
会议录	Intelligent Robotics and Applications - 12th International Conference, ICIRA 2019, Proceedings
会议录出版者	Springer Verlag
会议录出版地	Berlin
语种	英语
ISSN号	0302-9743
ISBN号	978-3-030-27537-2
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/25499]
专题	沈阳自动化研究所_机器人学研究室
通讯作者	Tang YD(唐延东)
作者单位	1.University of Chinese Academy of Sciences, Beijing 100049, China 2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110016, China 3.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
推荐引用方式 GB/T 7714	Zhang Z,Tan JD,Cui T,et al. Multi-scale Densely Connected Dehazing Network[C]. 见:. Shenyang, China. August 8-11, 2019.