NTIRE 2020 非均匀去雾挑战赛
计算机视觉与模式识别
2020-05-08 v1
摘要
本文回顾了 NTIRE 2020 图像非均匀去雾挑战赛（恢复雾图中的丰富细节）。我们聚焦于所提出的解决方案及其在 NH-Haze 上的评估结果，NH-Haze 是一个由 55 对户外记录的真实无雾与非均匀有雾图像组成的新数据集。NH-Haze 是首个提供真实图像的写实非均匀雾数据集。该非均匀雾是使用模拟真实雾场景条件的专业雾生成器产生的。168 名参与者注册了挑战赛，27 支队伍进入了最终测试阶段。所提出的解决方案衡量了图像去雾领域的最先进水平。
引用
@article{arxiv.2005.03457,
title = {NTIRE 2020 Challenge on NonHomogeneous Dehazing},
author = {Codruta O. Ancuti and Cosmin Ancuti and Florin-Alexandru Vasluianu and Radu Timofte and Jing Liu and Haiyan Wu and Yuan Xie and Yanyun Qu and Lizhuang Ma and Ziling Huang and Qili Deng and Ju-Chin Chao and Tsung-Shan Yang and Peng-Wen Chen and Po-Min Hsu and Tzu-Yi Liao and Chung-En Sun and Pei-Yuan Wu and Jeonghyeok Do and Jongmin Park and Munchurl Kim and Kareem Metwaly and Xuelu Li and Tiantong Guo and Vishal Monga and Mingzhao Yu and Venkateswararao Cherukuri and Shiue-Yuan Chuang and Tsung-Nan Lin and David Lee and Jerome Chang and Zhan-Han Wang and Yu-Bang Chang and Chang-Hong Lin and Yu Dong and Hongyu Zhou and Xiangzhen Kong and Sourya Dipta Das and Saikat Dutta and Xuan Zhao and Bing Ouyang and Dennis Estrada and Meiqi Wang and Tianqi Su and Siyi Chen and Bangyong Sun and Vincent Whannou de Dravo and Zhe Yu and Pratik Narang and Aryan Mehra and Navaneeth Raghunath and Murari Mandal},
journal= {arXiv preprint arXiv:2005.03457},
year = {2020}
}
备注
CVPR Workshops Proceedings 2020