ML Anthology

NTIRE 2020 Challenge on Image Demoireing: Methods and Results

Shanxin Yuan, Radu Timofte, Ales Leonardis, Gregory G. 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, Vien Gia An, 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
CVPRW 2020 pp. 1882-1893
doi:10.1109/CVPRW50498.2020.00238 /cvprw/2020/yuan2020cvprw-ntire/

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.

PDF CVPRW Semantic Scholar

Cite

Text

Yuan et al. "NTIRE 2020 Challenge on Image Demoireing: Methods and Results." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00238

Markdown

[Yuan et al. "NTIRE 2020 Challenge on Image Demoireing: Methods and Results." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/yuan2020cvprw-ntire/) doi:10.1109/CVPRW50498.2020.00238

BibTeX

@inproceedings{yuan2020cvprw-ntire,
  title     = {{NTIRE 2020 Challenge on Image Demoireing: Methods and Results}},
  author    = {Yuan, Shanxin and Timofte, Radu and Leonardis, Ales and Slabaugh, Gregory G. and Luo, Xiaotong and Zhang, Jiangtao and Qu, Yanyun and Hong, Ming and Xie, Yuan and Li, Cuihua and Xu, Dejia and Chu, Yihao and Sun, Qingyan and Liu, Shuai and Zong, Ziyao and Nan, Nan and Li, Chenghua and Kim, Sangmin and Nam, Hyungjoon and Kim, Jisu and Jeong, Jechang and Cheon, Manri and Yoon, Sung-Jun and Kang, Byungyeon and Lee, Junwoo and Zheng, Bolun and Liu, Xiaohong and Dai, Linhui and Chen, Jun and Cheng, Xi and Fu, Zhenyong and Yang, Jian and Lee, Chul and An, Vien Gia and Park, Hyunkook and Nathan, Sabari and Beham, M. Parisa and Roomi, S. Mohamed Mansoor and Lemarchand, Florian and Pelcat, Maxime and Nogues, Erwan and Puthussery, Densen and Hrishikesh, P. S and Jiji, C. V. and Sinha, Ashish and Zhao, Xuan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2020},
  pages     = {1882-1893},
  doi       = {10.1109/CVPRW50498.2020.00238},
  url       = {https://mlanthology.org/cvprw/2020/yuan2020cvprw-ntire/}
}