NTIRE 2020 challenge on image demoireing: Methods and results

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, Jechang; Cheon, M.; Yoon, S.-J.; Kang, B.; Lee, J.; Zheng, B.; Liu, X.; Dai, L.; Chen, J.; Cheng, X.; Fu, Z.; Yang, J.; Lee, C.; Vien, A.G.; Park, H.; Nathan, S.; Beham, M.P.; Mohamed, Mansoor Roomi S.; Lemarchand, F.; Pelcat, M.; Nogues, E.; Puthussery, D.; Hrishikesh, P.S.; Jiji, C.V.; Sinha, A.; Zhao, X.

doi:10.1109/CVPRW50498.2020.00238

상세 보기

NTIRE 2020 challenge on image demoireing: Methods and results

Yuan, S.;
Timofte, R.;
Leonardis, A.;
Slabaugh, G.;
Luo, X.;
외 41명

Citations

SCOPUS

38

초록

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.

키워드

Computer vision; Image reconstruction; Moire fringes; Restoration; Signal to noise ratio; Clean images; Ground truth; Image restoration and enhancements; Moire pattern; Peak signal to noise ratio; Single images; State of the art; Image enhancement

제목: NTIRE 2020 challenge on image demoireing: Methods and results

저자: 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, Jechang; Cheon, M.; Yoon, S.-J.; Kang, B.; Lee, J.; Zheng, B.; Liu, X.; Dai, L.; Chen, J.; Cheng, X.; Fu, Z.; Yang, J.; Lee, C.; Vien, A.G.; Park, H.; Nathan, S.; Beham, M.P.; Mohamed, Mansoor Roomi S.; Lemarchand, F.; Pelcat, M.; Nogues, E.; Puthussery, D.; Hrishikesh, P.S.; Jiji, C.V.; Sinha, A.; Zhao, X.

DOI: 10.1109/CVPRW50498.2020.00238

발행일: 2020-06

유형: Conference Paper

저널명: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

권: 2020-June

페이지: 1882 ~ 1893