NTIRE 2020挑战真实图像Denoising：数据集，方法和结果

论文标题

NTIRE 2020挑战真实图像Denoising：数据集，方法和结果

NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results

论文作者

Abdelhamed, Abdelrahman, Afifi, Mahmoud, Timofte, Radu, Brown, Michael S., Cao, Yue, Zhang, Zhilu, Zuo, Wangmeng, Zhang, Xiaoling, Liu, Jiye, Chen, Wendong, Wen, Changyuan, Liu, Meng, Lv, Shuailin, Zhang, Yunchao, Pan, Zhihong, Li, Baopu, Xi, Teng, Fan, Yanwen, Yu, Xiyu, Zhang, Gang, Liu, Jingtuo, Han, Junyu, Ding, Errui, Yu, Songhyun, Park, Bumjun, Jeong, Jechang, Liu, Shuai, Zong, Ziyao, Nan, Nan, Li, Chenghua, Yang, Zengli, Bao, Long, Wang, Shuangquan, Bai, Dongwoon, Lee, Jungwon, Kim, Youngjung, Rho, Kyeongha, Shin, Changyeop, Kim, Sungho, Tang, Pengliang, Zhao, Yiyun, Zhou, Yuqian, Fan, Yuchen, Huang, Thomas, Li, Zhihao, Shah, Nisarg A., Liu, Wei, Yan, Qiong, Zhao, Yuzhi, Możejko, Marcin, Latkowski, Tomasz, Treszczotko, Lukasz, Szafraniuk, Michał, Trojanowski, Krzysztof, Wu, Yanhong, Michelini, Pablo Navarrete, Hu, Fengshuo, Lu, Yunhua, Kim, Sujin, Kim, Wonjin, Lee, Jaayeon, Choi, Jang-Hwan, Zhussip, Magauiya, Khassenov, Azamat, Kim, Jong Hyun, Cho, Hwechul, Kansal, Priya, Nathan, Sabari, Ye, Zhangyu, Lu, Xiwen, Wu, Yaqi, Yang, Jiangxin, Cao, Yanlong, Tang, Siliang, Cao, Yanpeng, Maggioni, Matteo, Marras, Ioannis, Tanay, Thomas, Slabaugh, Gregory, Yan, Youliang, Kang, Myungjoo, Choi, Han-Soo, Song, Kyungmin, Xu, Shusong, Lu, Xiaomu, Wang, Tingniao, Lei, Chunxia, Liu, Bin, Gupta, Rajat, Kumar, Vineet

论文摘要

本文回顾了NTIRE 2020挑战对真实图像的挑战，重点是新引入的数据集，提议的方法及其结果。挑战是基于SIDD基准测试的上一张Ntire 2019挑战对真实图像的挑战的新版本。该挑战基于新收集的验证和测试图像数据集，因此，名为SIDD+。这项挑战有两条轨道，用于定量评估（1）拜耳 - 图案rawRGB和（2）标准RGB（SRGB）颜色空间中的图像性能。每个曲目〜250名注册参与者。总共22个团队提出了24种方法，参加了挑战的最后阶段。参与团队提出的方法代表了图像定位瞄准真噪声图像的当前最新性能。新收集的SIDD+数据集可在以下网址公开获取：https：//bit.ly/siddplus_data。

This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results. The challenge is a new version of the previous NTIRE 2019 challenge on real image denoising that was based on the SIDD benchmark. This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+. This challenge has two tracks for quantitatively evaluating image denoising performance in (1) the Bayer-pattern rawRGB and (2) the standard RGB (sRGB) color spaces. Each track ~250 registered participants. A total of 22 teams, proposing 24 methods, competed in the final phase of the challenge. The proposed methods by the participating teams represent the current state-of-the-art performance in image denoising targeting real noisy images. The newly collected SIDD+ datasets are publicly available at: https://bit.ly/siddplus_data.

下载PDF全文

下载文献需遵守相关版权规定

论文标题