Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges

Wenqi Ren, Jinshan Pan, Hua Zhang, Xiaochun Cao, Ming Hsuan Yang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
JournalInternational Journal of Computer Vision
DOIs
Publication statusAccepted/In press - 2019 Jan 1

Fingerprint

Neural networks
Experiments
Deep neural networks

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{55162dacc761423c94d4732e911e7a91,
title = "Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges",
abstract = "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.",
author = "Wenqi Ren and Jinshan Pan and Hua Zhang and Xiaochun Cao and Yang, {Ming Hsuan}",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s11263-019-01235-8",
language = "English",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",

}

Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges. / Ren, Wenqi; Pan, Jinshan; Zhang, Hua; Cao, Xiaochun; Yang, Ming Hsuan.

In: International Journal of Computer Vision, 01.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges

AU - Ren, Wenqi

AU - Pan, Jinshan

AU - Zhang, Hua

AU - Cao, Xiaochun

AU - Yang, Ming Hsuan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85073973241&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073973241&partnerID=8YFLogxK

U2 - 10.1007/s11263-019-01235-8

DO - 10.1007/s11263-019-01235-8

M3 - Article

AN - SCOPUS:85073973241

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

ER -