A Light Dual-Task Neural Network for Haze Removal

作     者：Zhang, Yu Wang, Xinchao Bi, Xiaojun Tao, Dacheng 

作者机构：IEEE College of Information and Communication Engineering Harbin Engineering University Heilongjiang150001 China UBTECH Sydney Artificial Intelligence Centre and the School of Information Technologies Faculty of Engineering and Information Technologies University of Sydney 6 Cleveland St DarlingtonNSW2008 Australia School of Software and Advanced Analytics Institute University of Technology Sydney 15 Broadway UltimoNSW2007 Australia Stevens Institute of Technology HobokenNJ07030 United States College of Information and Communication Engineering Harbin Engineering University Heilongjiang150001 China UBTECH Sydney Artificial Intelligence Centre School of Information Technologies Faculty of Engineering and Information Technologies University of Sydney 6 Cleveland St DarlingtonNSW2008 Australia 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2019年

核心收录：

主　　题：Image reconstruction 

摘      要：ingle-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. Copyright © 2019, The Authors. All rights reserved.