A Light Dual-Task Neural Network for Haze Removal

Zhang, Y; Wang, X; Bi, X; Tao, D

A Light Dual-Task Neural Network for Haze Removal

Zhang, Y

Wang, X Bi, X Tao, D

Permalink

Publication Type:: Journal Article
Citation:: IEEE Signal Processing Letters, 2018, 25 (8), pp. 1231 - 1235
Issue Date:: 2018-08-01

Closed Access

	Filename	Description	Size
	08392765.pdf	Published Version	721.35 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, Y https://orcid.org/0000-0002-8954-6741	en_US
dc.contributor.author	Wang, X	en_US
dc.contributor.author	Bi, X	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.date.issued	2018-08-01	en_US
dc.identifier.citation	IEEE Signal Processing Letters, 2018, 25 (8), pp. 1231 - 1235	en_US
dc.identifier.issn	1070-9908	en_US
dc.identifier.uri	http://hdl.handle.net/10453/128118
dc.description.abstract	© 1994-2012 IEEE. Single-image dehazing is a challenging problem due to its ill-posed nature. Existing methods rely on a suboptimal two-step approach, where an intermediate product like a depth map is estimated, based on which the haze-free image is subsequently generated using an artificial prior formula. In this paper, we propose a light dual-task Neural Network called LDTNet that restores the haze-free image in one shot. We use transmission map estimation as an auxiliary task to assist the main task, haze removal, in feature extraction and to enhance the generalization of the network. In LDTNet, the haze-free image and the transmission map are produced simultaneously. As a result, the artificial prior is reduced to the smallest extent. Extensive experiments demonstrate that our algorithm achieves superior performance against the state-of-the-art methods on both synthetic and real-world images.	en_US
dc.relation.ispartof	IEEE Signal Processing Letters	en_US
dc.relation.isbasedon	10.1109/LSP.2018.2849681	en_US
dc.subject.classification	Networking & Telecommunications	en_US
dc.title	A Light Dual-Task Neural Network for Haze Removal	en_US
dc.type	Journal Article
utslib.citation.volume	8	en_US
utslib.citation.volume	25	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	1005 Communications Technologies	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.issue	8	en_US
pubs.publication-status	Published	en_US
pubs.volume	25	en_US

Abstract:

© 1994-2012 IEEE. Single-image dehazing is a challenging problem due to its ill-posed nature. Existing methods rely on a suboptimal two-step approach, where an intermediate product like a depth map is estimated, based on which the haze-free image is subsequently generated using an artificial prior formula. In this paper, we propose a light dual-task Neural Network called LDTNet that restores the haze-free image in one shot. We use transmission map estimation as an auxiliary task to assist the main task, haze removal, in feature extraction and to enhance the generalization of the network. In LDTNet, the haze-free image and the transmission map are produced simultaneously. As a result, the artificial prior is reduced to the smallest extent. Extensive experiments demonstrate that our algorithm achieves superior performance against the state-of-the-art methods on both synthetic and real-world images.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/128118