This paper reviews the first-ever image demoireing challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ICCV 2019. This paper describes the challenge, and focuses on the proposed solutions and their results. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. A new dataset, called LCDMoire was created for this challenge, and consists of 10,200 synthetically generated image pairs (moire and clean ground truth). The challenge was divided into 2 tracks. Track 1 targeted fidelity, measuring the ability of demoire methods to obtain a moire-free image compared with the ground truth, while Track 2 examined the perceptual quality of demoire methods. The tracks had 60 and 39 registered participants, respectively. A total of eight teams competed in the final testing phase. The entries span the current the state-of-the-art in the image demoireing problem.
Cite
@article{arxiv.1911.03461,
title = {AIM 2019 Challenge on Image Demoireing: Methods and Results},
author = {Shanxin Yuan and Radu Timofte and Gregory Slabaugh and Ales Leonardis and Bolun Zheng and Xin Ye and Xiang Tian and Yaowu Chen and Xi Cheng and Zhenyong Fu and Jian Yang and Ming Hong and Wenying Lin and Wenjin Yang and Yanyun Qu and Hong-Kyu Shin and Joon-Yeon Kim and Sung-Jea Ko and Hang Dong and Yu Guo and Jie Wang and Xuan Ding and Zongyan Han and Sourya Dipta Das and Kuldeep Purohit and Praveen Kandula and Maitreya Suin and A. N. Rajagopalan},
journal= {arXiv preprint arXiv:1911.03461},
year = {2019}
}
Comments
arXiv admin note: text overlap with arXiv:1911.02498