SIA OpenIR  > 机器人学研究室
Multi-scale Densely Connected Dehazing Network
Cui T(崔童)1,2,3; Zhang Z(张箴)1,2,3; Tang YD(唐延东)1,2; Tan JD(田建东)1,2
Department机器人学研究室
Conference Name12th International Conference on Intelligent Robotics and Applications, ICIRA 2019
Conference DateAugust 8-11, 2019
Conference PlaceShenyang, China
Source PublicationIntelligent Robotics and Applications - 12th International Conference, ICIRA 2019, Proceedings
PublisherSpringer Verlag
Publication PlaceBerlin
2019
Pages594-604
Indexed ByEI
EI Accession number20193307310949
Contribution Rank1
ISSN0302-9743
ISBN978-3-030-27537-2
KeywordDeep learning image dehazing Multi-scale dense network One-in-all training Large-scale dataset
AbstractSingle 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.
Language英语
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/25499
Collection机器人学研究室
Corresponding AuthorTang YD(唐延东)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110016, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
Recommended Citation
GB/T 7714
Cui T,Zhang Z,Tang YD,et al. Multi-scale Densely Connected Dehazing Network[C]. Berlin:Springer Verlag,2019:594-604.
Files in This Item: Download All
File Name/Size DocType Version Access License
Multi-scale Densely (11511KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Cui T(崔童)]'s Articles
[Zhang Z(张箴)]'s Articles
[Tang YD(唐延东)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Cui T(崔童)]'s Articles
[Zhang Z(张箴)]'s Articles
[Tang YD(唐延东)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Cui T(崔童)]'s Articles
[Zhang Z(张箴)]'s Articles
[Tang YD(唐延东)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Multi-scale Densely Connected Dehazing Network.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.