跳到主要导航 跳到搜索 跳到主要内容

NTIRE 2019 challenge on real image denoising: Methods and results

  • Abdelrahman Abdelhamed
  • , Radu Timofte
  • , Michael S. Brown
  • , Songhyun Yu
  • , Bumjun Park
  • , Jechang Jeong
  • , Seung Won Jung
  • , Dong Wook Kim
  • , Jae Ryun Chung
  • , Jiaming Liu
  • , Yuzhi Wang
  • , Chi Hao Wu
  • , Qin Xu
  • , Chuan Wang
  • , Shaofan Cai
  • , Yifan DIng
  • , Haoqiang Fan
  • , Jue Wang
  • , Kai Zhang
  • , Wangmeng Zuo
  • Magauiya Zhussip, Dong Won Park, Shakarim Soltanayev, Se Young Chun, Zhiwei Xiong, Chang Chen, Muhammad Haris, Kazutoshi Akita, Tomoki Yoshida, Greg Shakhnarovich, Norimichi Ukita, Syed Waqas Zamir, Aditya Arora, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Sung Jea Ko, Dong Pan Lim, Seung Wook Kim, Seo Won Ji, Sang Won Lee, Wenyi Tang, Yuchen Fan, Yuqian Zhou, DIng Liu, Thomas S. Huang, Deyu Meng, Lei Zhang, Hongwei Yong, Yiyun Zhao, Pengliang Tang, Yue Lu, Raimondo Schettini, Simone Bianco, Simone Zini, Chi Li, Yang Wang, Zhiguo Cao
  • York University Toronto
  • Swiss Federal Institute of Technology Zurich
  • Hanyang University
  • Dongguk University
  • Megvii
  • Harbin Institute of Technology
  • Ulsan National Institute of Science and Technology
  • University of Science and Technology of China
  • Toyota Technological Institute at Chicago
  • Inception Institute of Artificial Intelligence
  • Korea University
  • University of Illinois at Urbana-Champaign
  • Alibaba Group Holding Ltd.
  • Beijing University of Posts and Telecommunications
  • University of Milan - Bicocca
  • Huazhong University of Science and Technology

科研成果: 书/报告/会议事项章节会议稿件同行评审

97 引用 (Scopus)

摘要

This paper reviews the NTIRE 2019 challenge on real image denoising with focus on the proposed methods and their results. The challenge has two tracks for quantitatively evaluating image denoising performance in (1) the Bayer-pattern raw-RGB and (2) the standard RGB (sRGB) color spaces. The tracks had 216 and 220 registered participants, respectively. A total of 15 teams, proposing 17 methods, competed in the final phase of the challenge. The proposed methods by the 15 teams represent the current state-of-the-art performance in image denoising targeting real noisy images.

源语言英语
主期刊名Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
出版商IEEE Computer Society
2197-2210
页数14
ISBN(电子版)9781728125060
DOI
出版状态已出版 - 6月 2019
已对外发布
活动32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 - Long Beach, 美国
期限: 16 6月 201920 6月 2019

出版系列

姓名IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
2019-June
ISSN(印刷版)2160-7508
ISSN(电子版)2160-7516

会议

会议32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
国家/地区美国
Long Beach
时期16/06/1920/06/19

学术指纹

探究 'NTIRE 2019 challenge on real image denoising: Methods and results' 的科研主题。它们共同构成独一无二的指纹。

引用此