期刊
INTERNATIONAL JOURNAL OF COMPUTER VISION
卷 128, 期 1, 页码 240-259出版社
SPRINGER
DOI: 10.1007/s11263-019-01235-8
关键词
Image dehazing; Image defogging; Convolutional neural network; Transmission map
资金
- National Key R&D Program of China [2018YFB0803701]
- Beijing Natural Science Foundation [KZ201910005007]
- National Natural Science Foundation of China [U1636214, U1803264, U1605252, 61802403, 61602464, 61872421, 61922043]
- Peng Cheng Laboratory Project of Guangdong Province [PCL2018KP004]
- Natural Science Foundation of Jiangsu Province [BK20180471, YF20180101]
- CCF-DiDi GAIA [YF20180101]
- CCF-Tencent Open Fund
- Zhejiang Lab's International Talent Fund for Young Professionals
- Open Projects Program of the National Laboratory of Pattern Recognition
- Directorate for Computer and Information Science and Engineering [CAREER 1149783]
Single image dehazing has been a challenging problem which aims to recover clear images from hazy ones. The performance of existing image dehazing methods is limited by hand-designed features and priors. In this paper, we propose a multi-scale deep neural network for single image dehazing by learning the mapping between hazy images and their transmission maps. The proposed algorithm consists of a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale net which refines dehazed results locally. To train the multi-scale deep network, we synthesize a dataset comprised of hazy images and corresponding transmission maps based on the NYU Depth dataset. In addition, we propose a holistic edge guided network to refine edges of the estimated transmission map. Extensive experiments demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods on both synthetic and real-world images in terms of quality and speed.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据