PMS-Net: Robust haze removal based on patch map for single images

Wei Ting Chen; Jian Jiun Ding; Sy Yen Kuo

doi:10.1109/CVPR.2019.01195

PMS-Net: Robust haze removal based on patch map for single images

Wei Ting Chen^*, Jian Jiun Ding, Sy Yen Kuo

^*Corresponding author for this work

National Taiwan University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

81 Scopus citations

Abstract

In this paper, we proposed a novel haze removal algorithm based on a new feature called the patch map. Conventional patch-based haze removal algorithms (e.g. the Dark Channel prior) usually performs dehazing with a fixed patch size. However, it may produce several problems in recovered results such as oversaturation and color distortion. Therefore, in this paper, we designed an adaptive and automatic patch size selection model called the Patch Map Selection Network (PMS-Net) to select the patch size corresponding to each pixel. This network is designed based on the convolutional neural network (CNN), which can generate the patch map from the image to image. Experimental results on both synthesized and real-world hazy images show that, with the combination of the proposed PMS-Net, the performance in haze removal is much better than that of other state-of-the-art algorithms and we can address the problems caused by the fixed patch size.

Original language	English
Title of host publication	Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Publisher	IEEE Computer Society
Pages	11673-11681
Number of pages	9
ISBN (Electronic)	9781728132938
DOIs	https://doi.org/10.1109/CVPR.2019.01195
State	Published - 06 2019
Externally published	Yes
Event	32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, United States Duration: 16 06 2019 → 20 06 2019

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2019-June
ISSN (Print)	1063-6919

Conference

Conference	32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Country/Territory	United States
City	Long Beach
Period	16/06/19 → 20/06/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Computational Photography
Computer Vision Theory

Access to Document

10.1109/CVPR.2019.01195

Cite this

Chen, W. T., Ding, J. J., & Kuo, S. Y. (2019). PMS-Net: Robust haze removal based on patch map for single images. In Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 (pp. 11673-11681). Article 8954465 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2019-June). IEEE Computer Society. https://doi.org/10.1109/CVPR.2019.01195

@inproceedings{00d2915953bd4467bc998efeab7cd175,

title = "PMS-Net: Robust haze removal based on patch map for single images",

abstract = "In this paper, we proposed a novel haze removal algorithm based on a new feature called the patch map. Conventional patch-based haze removal algorithms (e.g. the Dark Channel prior) usually performs dehazing with a fixed patch size. However, it may produce several problems in recovered results such as oversaturation and color distortion. Therefore, in this paper, we designed an adaptive and automatic patch size selection model called the Patch Map Selection Network (PMS-Net) to select the patch size corresponding to each pixel. This network is designed based on the convolutional neural network (CNN), which can generate the patch map from the image to image. Experimental results on both synthesized and real-world hazy images show that, with the combination of the proposed PMS-Net, the performance in haze removal is much better than that of other state-of-the-art algorithms and we can address the problems caused by the fixed patch size.",

keywords = "Computational Photography, Computer Vision Theory",

author = "Chen, {Wei Ting} and Ding, {Jian Jiun} and Kuo, {Sy Yen}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 ; Conference date: 16-06-2019 Through 20-06-2019",

year = "2019",

month = jun,

doi = "10.1109/CVPR.2019.01195",

language = "英语",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "11673--11681",

booktitle = "Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019",

address = "美国",

}

Chen, WT, Ding, JJ & Kuo, SY 2019, PMS-Net: Robust haze removal based on patch map for single images. in Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019., 8954465, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2019-June, IEEE Computer Society, pp. 11673-11681, 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, United States, 16/06/19. https://doi.org/10.1109/CVPR.2019.01195

PMS-Net: Robust haze removal based on patch map for single images. / Chen, Wei Ting; Ding, Jian Jiun; Kuo, Sy Yen.
Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019. IEEE Computer Society, 2019. p. 11673-11681 8954465 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2019-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - PMS-Net

T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019

AU - Chen, Wei Ting

AU - Ding, Jian Jiun

AU - Kuo, Sy Yen

PY - 2019/6

Y1 - 2019/6

N2 - In this paper, we proposed a novel haze removal algorithm based on a new feature called the patch map. Conventional patch-based haze removal algorithms (e.g. the Dark Channel prior) usually performs dehazing with a fixed patch size. However, it may produce several problems in recovered results such as oversaturation and color distortion. Therefore, in this paper, we designed an adaptive and automatic patch size selection model called the Patch Map Selection Network (PMS-Net) to select the patch size corresponding to each pixel. This network is designed based on the convolutional neural network (CNN), which can generate the patch map from the image to image. Experimental results on both synthesized and real-world hazy images show that, with the combination of the proposed PMS-Net, the performance in haze removal is much better than that of other state-of-the-art algorithms and we can address the problems caused by the fixed patch size.

AB - In this paper, we proposed a novel haze removal algorithm based on a new feature called the patch map. Conventional patch-based haze removal algorithms (e.g. the Dark Channel prior) usually performs dehazing with a fixed patch size. However, it may produce several problems in recovered results such as oversaturation and color distortion. Therefore, in this paper, we designed an adaptive and automatic patch size selection model called the Patch Map Selection Network (PMS-Net) to select the patch size corresponding to each pixel. This network is designed based on the convolutional neural network (CNN), which can generate the patch map from the image to image. Experimental results on both synthesized and real-world hazy images show that, with the combination of the proposed PMS-Net, the performance in haze removal is much better than that of other state-of-the-art algorithms and we can address the problems caused by the fixed patch size.

KW - Computational Photography

KW - Computer Vision Theory

UR - http://www.scopus.com/inward/record.url?scp=85078736805&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2019.01195

DO - 10.1109/CVPR.2019.01195

M3 - 会议稿件

AN - SCOPUS:85078736805

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 11673

EP - 11681

BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019

PB - IEEE Computer Society

Y2 - 16 June 2019 through 20 June 2019

ER -

Chen WT, Ding JJ, Kuo SY. PMS-Net: Robust haze removal based on patch map for single images. In Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019. IEEE Computer Society. 2019. p. 11673-11681. 8954465. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR.2019.01195

PMS-Net: Robust haze removal based on patch map for single images

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this