NTIRE 2019 image dehazing challenge report

Codruta O. Ancuti; Cosmin Ancuti; Radu Timofte; Luc Van Gool; Lei Zhang; Ming Hsuan Yang; Tiantong Guo; Xuelu Li; Venkateswararao Cherukuri; Vishal Monga; Hao Jiang; Siyuan Yang; Yan Liu; Xiaochao Qu; Pengfei Wan; Dongwon Park; Se Young Chun; Ming Hong; Jinying Huang; Yizi Chen; Shuxin Chen; Bomin Wang; Pablo Navarrete Michelini; Hanwen Liu; Dan Zhu; Jing Liu; Sanchayan Santra; Ranjan Mondal; Bhabatosh Chanda; Peter Morales; Tzofi Klinghoffer; Le Manh Quan; Yong Guk Kim; Xiao Liang; Runde Li; Jinshan Pan; Jinhui Tang; Kuldeep Purohit; Maitreya Suin; A. N. Rajagopalan; Raimondo Schettini; Simone Bianco; Flavio Piccoli; C. Cusano; Luigi Celona; Sunhee Hwang; Yu Seung Ma; Hyeran Byun; Subrahmanyam Murala; Akshay Dudhane; Harsh Aulakh; Tianxiang Zheng; Tao Zhang; Weining Qin; Runnan Zhou; Shanhu Wang; Jean Philippe Tarel; Chuansheng Wang; Jiawei Wu

doi:10.1109/CVPRW.2019.00277

NTIRE 2019 image dehazing challenge report

Codruta O. Ancuti, Cosmin Ancuti, Radu Timofte, Luc Van Gool, Lei Zhang, Ming Hsuan Yang, Tiantong Guo, Xuelu Li, Venkateswararao Cherukuri, Vishal Monga, Hao Jiang, Siyuan Yang, Yan Liu, Xiaochao Qu, Pengfei Wan, Dongwon Park, Se Young Chun, Ming Hong, Jinying Huang, Yizi ChenShuxin Chen, Bomin Wang, Pablo Navarrete Michelini, Hanwen Liu, Dan Zhu, Jing Liu, Sanchayan Santra, Ranjan Mondal, Bhabatosh Chanda, Peter Morales, Tzofi Klinghoffer, Le Manh Quan, Yong Guk Kim, Xiao Liang, Runde Li, Jinshan Pan, Jinhui Tang, Kuldeep Purohit, Maitreya Suin, A. N. Rajagopalan, Raimondo Schettini, Simone Bianco, Flavio Piccoli, C. Cusano, Luigi Celona, Sunhee Hwang, Yu Seung Ma, Hyeran Byun, Subrahmanyam Murala, Akshay Dudhane, Harsh Aulakh, Tianxiang Zheng, Tao Zhang, Weining Qin, Runnan Zhou, Shanhu Wang, Jean Philippe Tarel, Chuansheng Wang, Jiawei Wu

College of Computing

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

23 Citations (Scopus)

Abstract

This paper reviews the second NTIRE challenge on image dehazing (restoration of rich details in hazy image) with focus on proposed solutions and results. The training data consists from 55 hazy images (with dense haze generated in an indoor or outdoor environment) and their corresponding ground truth (haze-free) images of the same scene. The dense haze has been produced using a professional haze/fog generator that imitates the real conditions of haze scenes. The evaluation consists from the comparison of the dehazed images with the ground truth images. The dehazing process was learnable through provided pairs of haze-free and hazy train images. There were ~ 270 registered participants and 23 teams competed in the final testing phase. They gauge the state-of-the-art in image dehazing.

Original language	English
Title of host publication	Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
Publisher	IEEE Computer Society
Pages	2241-2253
Number of pages	13
ISBN (Electronic)	9781728125060
DOIs	https://doi.org/10.1109/CVPRW.2019.00277
Publication status	Published - 2019 Jun
Event	32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 - Long Beach, United States Duration: 2019 Jun 16 → 2019 Jun 20

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2019-June
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
Country/Territory	United States
City	Long Beach
Period	19/6/16 → 19/6/20

Bibliographical note

Funding Information:
We thank the NTIRE 2019 sponsors: Huawei Technologies Co. Ltd., NVIDIA Corp., Amazon.com, Inc., Sam-sung, MediaTek, Oppo and ETH Zurich (Computer Vision Lab). Part of this work was supported by research grant GNaC2018 - ARUT, no. 1361-01.02.2019, financed by Politehnica University of Timisoara. Part of this work was supported by 2020 European Union Research and Innovation Horizon 2020 under the grant agreement Marie Sklodowska-Curie No 712949 (TECNIOspring PLUS), as well as the Agency for the Competitiveness of the Company of the Generalitat de Catalunya - ACCIO: TECSPR17-1-0054.

Publisher Copyright:
© 2019 IEEE.

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CVPRW.2019.00277

Cite this

Ancuti, C. O., Ancuti, C., Timofte, R., Van Gool, L., Zhang, L., Yang, M. H., Guo, T., Li, X., Cherukuri, V., Monga, V., Jiang, H., Yang, S., Liu, Y., Qu, X., Wan, P., Park, D., Chun, S. Y., Hong, M., Huang, J., ... Wu, J. (2019). NTIRE 2019 image dehazing challenge report. In Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 (pp. 2241-2253). [9025690] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2019-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2019.00277

@inproceedings{424ebbb2839f4723ba1572a2be4347d2,

title = "NTIRE 2019 image dehazing challenge report",

abstract = "This paper reviews the second NTIRE challenge on image dehazing (restoration of rich details in hazy image) with focus on proposed solutions and results. The training data consists from 55 hazy images (with dense haze generated in an indoor or outdoor environment) and their corresponding ground truth (haze-free) images of the same scene. The dense haze has been produced using a professional haze/fog generator that imitates the real conditions of haze scenes. The evaluation consists from the comparison of the dehazed images with the ground truth images. The dehazing process was learnable through provided pairs of haze-free and hazy train images. There were ~ 270 registered participants and 23 teams competed in the final testing phase. They gauge the state-of-the-art in image dehazing.",

author = "Ancuti, {Codruta O.} and Cosmin Ancuti and Radu Timofte and {Van Gool}, Luc and Lei Zhang and Yang, {Ming Hsuan} and Tiantong Guo and Xuelu Li and Venkateswararao Cherukuri and Vishal Monga and Hao Jiang and Siyuan Yang and Yan Liu and Xiaochao Qu and Pengfei Wan and Dongwon Park and Chun, {Se Young} and Ming Hong and Jinying Huang and Yizi Chen and Shuxin Chen and Bomin Wang and Michelini, {Pablo Navarrete} and Hanwen Liu and Dan Zhu and Jing Liu and Sanchayan Santra and Ranjan Mondal and Bhabatosh Chanda and Peter Morales and Tzofi Klinghoffer and Quan, {Le Manh} and Kim, {Yong Guk} and Xiao Liang and Runde Li and Jinshan Pan and Jinhui Tang and Kuldeep Purohit and Maitreya Suin and Rajagopalan, {A. N.} and Raimondo Schettini and Simone Bianco and Flavio Piccoli and C. Cusano and Luigi Celona and Sunhee Hwang and Ma, {Yu Seung} and Hyeran Byun and Subrahmanyam Murala and Akshay Dudhane and Harsh Aulakh and Tianxiang Zheng and Tao Zhang and Weining Qin and Runnan Zhou and Shanhu Wang and Tarel, {Jean Philippe} and Chuansheng Wang and Jiawei Wu",

note = "Funding Information: We thank the NTIRE 2019 sponsors: Huawei Technologies Co. Ltd., NVIDIA Corp., Amazon.com, Inc., Sam-sung, MediaTek, Oppo and ETH Zurich (Computer Vision Lab). Part of this work was supported by research grant GNaC2018 - ARUT, no. 1361-01.02.2019, financed by Politehnica University of Timisoara. Part of this work was supported by 2020 European Union Research and Innovation Horizon 2020 under the grant agreement Marie Sklodowska-Curie No 712949 (TECNIOspring PLUS), as well as the Agency for the Competitiveness of the Company of the Generalitat de Catalunya - ACCIO: TECSPR17-1-0054. Publisher Copyright: {\textcopyright} 2019 IEEE.; 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 ; Conference date: 16-06-2019 Through 20-06-2019",

year = "2019",

month = jun,

doi = "10.1109/CVPRW.2019.00277",

language = "English",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "2241--2253",

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

address = "United States",

}

Ancuti, CO, Ancuti, C, Timofte, R, Van Gool, L, Zhang, L, Yang, MH, Guo, T, Li, X, Cherukuri, V, Monga, V, Jiang, H, Yang, S, Liu, Y, Qu, X, Wan, P, Park, D, Chun, SY, Hong, M, Huang, J, Chen, Y, Chen, S, Wang, B, Michelini, PN, Liu, H, Zhu, D, Liu, J, Santra, S, Mondal, R, Chanda, B, Morales, P, Klinghoffer, T, Quan, LM, Kim, YG, Liang, X, Li, R, Pan, J, Tang, J, Purohit, K, Suin, M, Rajagopalan, AN, Schettini, R, Bianco, S, Piccoli, F, Cusano, C, Celona, L, Hwang, S, Ma, YS, Byun, H, Murala, S, Dudhane, A, Aulakh, H, Zheng, T, Zhang, T, Qin, W, Zhou, R, Wang, S, Tarel, JP, Wang, C & Wu, J 2019, NTIRE 2019 image dehazing challenge report. in Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019., 9025690, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2019-June, IEEE Computer Society, pp. 2241-2253, 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019, Long Beach, United States, 19/6/16. https://doi.org/10.1109/CVPRW.2019.00277

NTIRE 2019 image dehazing challenge report. / Ancuti, Codruta O.; Ancuti, Cosmin; Timofte, Radu et al.

Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019. IEEE Computer Society, 2019. p. 2241-2253 9025690 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2019-June).

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

TY - GEN

T1 - NTIRE 2019 image dehazing challenge report

AU - Ancuti, Codruta O.

AU - Ancuti, Cosmin

AU - Timofte, Radu

AU - Van Gool, Luc

AU - Zhang, Lei

AU - Yang, Ming Hsuan

AU - Guo, Tiantong

AU - Li, Xuelu

AU - Cherukuri, Venkateswararao

AU - Monga, Vishal

AU - Jiang, Hao

AU - Yang, Siyuan

AU - Liu, Yan

AU - Qu, Xiaochao

AU - Wan, Pengfei

AU - Park, Dongwon

AU - Chun, Se Young

AU - Hong, Ming

AU - Huang, Jinying

AU - Chen, Yizi

AU - Chen, Shuxin

AU - Wang, Bomin

AU - Michelini, Pablo Navarrete

AU - Liu, Hanwen

AU - Zhu, Dan

AU - Liu, Jing

AU - Santra, Sanchayan

AU - Mondal, Ranjan

AU - Chanda, Bhabatosh

AU - Morales, Peter

AU - Klinghoffer, Tzofi

AU - Quan, Le Manh

AU - Kim, Yong Guk

AU - Liang, Xiao

AU - Li, Runde

AU - Pan, Jinshan

AU - Tang, Jinhui

AU - Purohit, Kuldeep

AU - Suin, Maitreya

AU - Rajagopalan, A. N.

AU - Schettini, Raimondo

AU - Bianco, Simone

AU - Piccoli, Flavio

AU - Cusano, C.

AU - Celona, Luigi

AU - Hwang, Sunhee

AU - Ma, Yu Seung

AU - Byun, Hyeran

AU - Murala, Subrahmanyam

AU - Dudhane, Akshay

AU - Aulakh, Harsh

AU - Zheng, Tianxiang

AU - Zhang, Tao

AU - Qin, Weining

AU - Zhou, Runnan

AU - Wang, Shanhu

AU - Tarel, Jean Philippe

AU - Wang, Chuansheng

AU - Wu, Jiawei

N1 - Funding Information: We thank the NTIRE 2019 sponsors: Huawei Technologies Co. Ltd., NVIDIA Corp., Amazon.com, Inc., Sam-sung, MediaTek, Oppo and ETH Zurich (Computer Vision Lab). Part of this work was supported by research grant GNaC2018 - ARUT, no. 1361-01.02.2019, financed by Politehnica University of Timisoara. Part of this work was supported by 2020 European Union Research and Innovation Horizon 2020 under the grant agreement Marie Sklodowska-Curie No 712949 (TECNIOspring PLUS), as well as the Agency for the Competitiveness of the Company of the Generalitat de Catalunya - ACCIO: TECSPR17-1-0054. Publisher Copyright: © 2019 IEEE.

PY - 2019/6

Y1 - 2019/6

N2 - This paper reviews the second NTIRE challenge on image dehazing (restoration of rich details in hazy image) with focus on proposed solutions and results. The training data consists from 55 hazy images (with dense haze generated in an indoor or outdoor environment) and their corresponding ground truth (haze-free) images of the same scene. The dense haze has been produced using a professional haze/fog generator that imitates the real conditions of haze scenes. The evaluation consists from the comparison of the dehazed images with the ground truth images. The dehazing process was learnable through provided pairs of haze-free and hazy train images. There were ~ 270 registered participants and 23 teams competed in the final testing phase. They gauge the state-of-the-art in image dehazing.

AB - This paper reviews the second NTIRE challenge on image dehazing (restoration of rich details in hazy image) with focus on proposed solutions and results. The training data consists from 55 hazy images (with dense haze generated in an indoor or outdoor environment) and their corresponding ground truth (haze-free) images of the same scene. The dense haze has been produced using a professional haze/fog generator that imitates the real conditions of haze scenes. The evaluation consists from the comparison of the dehazed images with the ground truth images. The dehazing process was learnable through provided pairs of haze-free and hazy train images. There were ~ 270 registered participants and 23 teams competed in the final testing phase. They gauge the state-of-the-art in image dehazing.

UR - http://www.scopus.com/inward/record.url?scp=85081948837&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85081948837&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2019.00277

DO - 10.1109/CVPRW.2019.00277

M3 - Conference contribution

AN - SCOPUS:85081948837

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 2241

EP - 2253

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

PB - IEEE Computer Society

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

Y2 - 16 June 2019 through 20 June 2019

ER -

Ancuti CO, Ancuti C, Timofte R, Van Gool L, Zhang L, Yang MH et al. NTIRE 2019 image dehazing challenge report. In Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019. IEEE Computer Society. 2019. p. 2241-2253. 9025690. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW.2019.00277

NTIRE 2019 image dehazing challenge report

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this