NTIRE 2020 challenge on image demoireing: Methods and results

Shanxin Yuan; Radu Timofte; Ales Leonardis; Gregory Slabaugh; Xiaotong Luo; Jiangtao Zhang; Yanyun Qu; Ming Hong; Yuan Xie; Cuihua Li; Dejia Xu; Yihao Chu; Qingyan Sun; Shuai Liu; Ziyao Zong; Nan Nan; Chenghua Li; Sangmin Kim; Hyungjoon Nam; Jisu Kim; Jechang Jeong; Manri Cheon; Sung Jun Yoon; Byungyeon Kang; Junwoo Lee; Bolun Zheng; Xiaohong Liu; Linhui Dai; Jun Chen; Xi Cheng; Zhenyong Fu; Jian Yang; Chul Lee; An Gia Vien; Hyunkook Park; Sabari Nathan; M. Parisa Beham; S. Mohamed Mansoor Roomi; Florian Lemarchand; Maxime Pelcat; Erwan Nogues; Densen Puthussery; P. S. Hrishikesh; C. V. Jiji; Ashish Sinha; Xuan Zhao

doi:10.1109/CVPRW50498.2020.00238

NTIRE 2020 challenge on image demoireing: Methods and results

Shanxin Yuan, Radu Timofte, Ales Leonardis, Gregory Slabaugh, Xiaotong Luo, Jiangtao Zhang, Yanyun Qu, Ming Hong, Yuan Xie, Cuihua Li, Dejia Xu, Yihao Chu, Qingyan Sun, Shuai Liu, Ziyao Zong, Nan Nan, Chenghua Li, Sangmin Kim, Hyungjoon Nam, Jisu KimJechang Jeong, Manri Cheon, Sung Jun Yoon, Byungyeon Kang, Junwoo Lee, Bolun Zheng, Xiaohong Liu, Linhui Dai, Jun Chen, Xi Cheng, Zhenyong Fu, Jian Yang, Chul Lee, An Gia Vien, Hyunkook Park, Sabari Nathan, M. Parisa Beham, S. Mohamed Mansoor Roomi, Florian Lemarchand, Maxime Pelcat, Erwan Nogues, Densen Puthussery, P. S. Hrishikesh, C. V. Jiji, Ashish Sinha, Xuan Zhao

Division of AI Software Convergence

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

33 Scopus citations

Abstract

This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. The challenge was divided into two tracks. Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image. Track 2 focused on the burst demoireing problem, where a set of degraded moire images of the same scene were provided as input, with the goal of producing a single demoired image as output. The methods were ranked in terms of their fidelity, measured using the peak signal-to-noise ratio (PSNR) between the ground truth clean images and the restored images produced by the participants' methods. The tracks had 142 and 99 registered participants, respectively, with a total of 14 and 6 submissions in the final testing stage. The entries span the current state-of-the-art in image and burst image demoireing problems.

Original language	English
Title of host publication	Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
Publisher	IEEE Computer Society
Pages	1882-1893
Number of pages	12
ISBN (Electronic)	9781728193601
DOIs	https://doi.org/10.1109/CVPRW50498.2020.00238
State	Published - Jun 2020
Event	2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 - Virtual, Online, United States Duration: 14 Jun 2020 → 19 Jun 2020

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2020-June
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
Country/Territory	United States
City	Virtual, Online
Period	14/06/20 → 19/06/20

Access to Document

10.1109/CVPRW50498.2020.00238

Cite this

Yuan, S., Timofte, R., Leonardis, A., Slabaugh, G., Luo, X., Zhang, J., Qu, Y., Hong, M., Xie, Y., Li, C., Xu, D., Chu, Y., Sun, Q., Liu, S., Zong, Z., Nan, N., Li, C., Kim, S., Nam, H., ... Zhao, X. (2020). NTIRE 2020 challenge on image demoireing: Methods and results. In Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 (pp. 1882-1893). Article 9150683 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2020-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW50498.2020.00238

@inproceedings{2de17db3d39141da97d8011a2df8fea9,

title = "NTIRE 2020 challenge on image demoireing: Methods and results",

abstract = "This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. The challenge was divided into two tracks. Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image. Track 2 focused on the burst demoireing problem, where a set of degraded moire images of the same scene were provided as input, with the goal of producing a single demoired image as output. The methods were ranked in terms of their fidelity, measured using the peak signal-to-noise ratio (PSNR) between the ground truth clean images and the restored images produced by the participants' methods. The tracks had 142 and 99 registered participants, respectively, with a total of 14 and 6 submissions in the final testing stage. The entries span the current state-of-the-art in image and burst image demoireing problems.",

author = "Shanxin Yuan and Radu Timofte and Ales Leonardis and Gregory Slabaugh and Xiaotong Luo and Jiangtao Zhang and Yanyun Qu and Ming Hong and Yuan Xie and Cuihua Li and Dejia Xu and Yihao Chu and Qingyan Sun and Shuai Liu and Ziyao Zong and Nan Nan and Chenghua Li and Sangmin Kim and Hyungjoon Nam and Jisu Kim and Jechang Jeong and Manri Cheon and Yoon, {Sung Jun} and Byungyeon Kang and Junwoo Lee and Bolun Zheng and Xiaohong Liu and Linhui Dai and Jun Chen and Xi Cheng and Zhenyong Fu and Jian Yang and Chul Lee and Vien, {An Gia} and Hyunkook Park and Sabari Nathan and Beham, {M. Parisa} and {Mohamed Mansoor Roomi}, S. and Florian Lemarchand and Maxime Pelcat and Erwan Nogues and Densen Puthussery and Hrishikesh, {P. S.} and Jiji, {C. V.} and Ashish Sinha and Xuan Zhao",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 ; Conference date: 14-06-2020 Through 19-06-2020",

year = "2020",

month = jun,

doi = "10.1109/CVPRW50498.2020.00238",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "1882--1893",

booktitle = "Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020",

address = "United States",

}

Yuan, S, Timofte, R, Leonardis, A, Slabaugh, G, Luo, X, Zhang, J, Qu, Y, Hong, M, Xie, Y, Li, C, Xu, D, Chu, Y, Sun, Q, Liu, S, Zong, Z, Nan, N, Li, C, Kim, S, Nam, H, Kim, J, Jeong, J, Cheon, M, Yoon, SJ, Kang, B, Lee, J, Zheng, B, Liu, X, Dai, L, Chen, J, Cheng, X, Fu, Z, Yang, J, Lee, C, Vien, AG, Park, H, Nathan, S, Beham, MP, Mohamed Mansoor Roomi, S, Lemarchand, F, Pelcat, M, Nogues, E, Puthussery, D, Hrishikesh, PS, Jiji, CV, Sinha, A & Zhao, X 2020, NTIRE 2020 challenge on image demoireing: Methods and results. in Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020., 9150683, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2020-June, IEEE Computer Society, pp. 1882-1893, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020, Virtual, Online, United States, 14/06/20. https://doi.org/10.1109/CVPRW50498.2020.00238

NTIRE 2020 challenge on image demoireing: Methods and results. / Yuan, Shanxin; Timofte, Radu; Leonardis, Ales et al.
Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020. IEEE Computer Society, 2020. p. 1882-1893 9150683 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2020-June).

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

TY - GEN

T1 - NTIRE 2020 challenge on image demoireing

T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020

AU - Yuan, Shanxin

AU - Timofte, Radu

AU - Leonardis, Ales

AU - Slabaugh, Gregory

AU - Luo, Xiaotong

AU - Zhang, Jiangtao

AU - Qu, Yanyun

AU - Hong, Ming

AU - Xie, Yuan

AU - Li, Cuihua

AU - Xu, Dejia

AU - Chu, Yihao

AU - Sun, Qingyan

AU - Liu, Shuai

AU - Zong, Ziyao

AU - Nan, Nan

AU - Li, Chenghua

AU - Kim, Sangmin

AU - Nam, Hyungjoon

AU - Kim, Jisu

AU - Jeong, Jechang

AU - Cheon, Manri

AU - Yoon, Sung Jun

AU - Kang, Byungyeon

AU - Lee, Junwoo

AU - Zheng, Bolun

AU - Liu, Xiaohong

AU - Dai, Linhui

AU - Chen, Jun

AU - Cheng, Xi

AU - Fu, Zhenyong

AU - Yang, Jian

AU - Lee, Chul

AU - Vien, An Gia

AU - Park, Hyunkook

AU - Nathan, Sabari

AU - Beham, M. Parisa

AU - Mohamed Mansoor Roomi, S.

AU - Lemarchand, Florian

AU - Pelcat, Maxime

AU - Nogues, Erwan

AU - Puthussery, Densen

AU - Hrishikesh, P. S.

AU - Jiji, C. V.

AU - Sinha, Ashish

AU - Zhao, Xuan

PY - 2020/6

Y1 - 2020/6

N2 - This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. The challenge was divided into two tracks. Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image. Track 2 focused on the burst demoireing problem, where a set of degraded moire images of the same scene were provided as input, with the goal of producing a single demoired image as output. The methods were ranked in terms of their fidelity, measured using the peak signal-to-noise ratio (PSNR) between the ground truth clean images and the restored images produced by the participants' methods. The tracks had 142 and 99 registered participants, respectively, with a total of 14 and 6 submissions in the final testing stage. The entries span the current state-of-the-art in image and burst image demoireing problems.

AB - This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. The challenge was divided into two tracks. Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image. Track 2 focused on the burst demoireing problem, where a set of degraded moire images of the same scene were provided as input, with the goal of producing a single demoired image as output. The methods were ranked in terms of their fidelity, measured using the peak signal-to-noise ratio (PSNR) between the ground truth clean images and the restored images produced by the participants' methods. The tracks had 142 and 99 registered participants, respectively, with a total of 14 and 6 submissions in the final testing stage. The entries span the current state-of-the-art in image and burst image demoireing problems.

UR - http://www.scopus.com/inward/record.url?scp=85090128007&partnerID=8YFLogxK

U2 - 10.1109/CVPRW50498.2020.00238

DO - 10.1109/CVPRW50498.2020.00238

M3 - Conference contribution

AN - SCOPUS:85090128007

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

SP - 1882

EP - 1893

BT - Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020

PB - IEEE Computer Society

Y2 - 14 June 2020 through 19 June 2020

ER -

Yuan S, Timofte R, Leonardis A, Slabaugh G, Luo X, Zhang J et al. NTIRE 2020 challenge on image demoireing: Methods and results. In Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020. IEEE Computer Society. 2020. p. 1882-1893. 9150683. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW50498.2020.00238

NTIRE 2020 challenge on image demoireing: Methods and results

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this