Publications

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication


Year(s) from:  to 
Author:
Keywords (separated by spaces):

NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results

Radu Timofte and Eirikur Agustsson and Luc Van Gool and Ming-Hsuan Yang and Lei Zhang and Bee Lim and Sanghyun Son and Heewon Kim and Seungjun Nah and Kyoung Mu Lee and Xintao Wang and Yapeng Tian and Ke Yu and Yulun Zhang and Shixiang Wu and Chao Dong and Liang Lin and Yu Qiao and Chen Change Loy and Woong Bae and Jaejun Yoo and Yoseob Han and Jong Chul Ye and Jae-Seok Choi and Munchurl Kim and Yuchen Fan and Jiahui Yu and Wei Han and Ding Liu and Haichao Yu and Zhangyang Wang and Honghui Shi and Xinchao Wang and Thomas S. Huang and Yunjin Chen and Kai Zhang and Wangmeng Zuo and Zhimin Tang and Linkai Luo and Shaohui Li and Min Fu and Lei Cao and Wen Heng and Giang Bui and Truc Le and Ye Duan and Dacheng Tao and Ruxin Wang and Xu Lin and Jianxin Pang and Jinchang Xu and Yu Zhao and Xiangyu Xu and Jinshan Pan and Deqing Sun and Yujin Zhang and Xibin Song and Yuchao Dai and Xueying Qin and Xuan-Phung Huynh and Tiantong Guo and Hojjat Seyed Mousavi and Tiep Huu Vu and Vishal Monga and Cristovao Cruz and Karen Egiazarian and Vladimir Katkovnik and Rakesh Mehta and Arnav Kumar Jain and Abhinav Agarwalla and Ch V Sai Praveen and Ruofan Zhou and Hongdiao Wen and Che Zhu and Zhiqiang Xia and Zhengtao Wang and Qi Guo
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017) Workshops
US, July 2017

Abstract

This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. A new DIVerse 2K resolution image dataset (DIV2K) was employed. The challenge had 6 competitions divided into 2 tracks with 3 magnification factors each. Track 1 employed the standard bicubic downscaling setup, while Track 2 had unknown downscaling operators (blur kernel and decimation) but learnable through low and high res train images. Each competition had ∌ 100 registered participants and 20 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.


Download in pdf format
@InProceedings{eth_biwi_01364,
  author = {Radu Timofte and Eirikur Agustsson and Luc Van Gool and Ming-Hsuan Yang and Lei Zhang and Bee Lim and Sanghyun Son and Heewon Kim and Seungjun Nah and Kyoung Mu Lee and Xintao Wang and Yapeng Tian and Ke Yu and Yulun Zhang and Shixiang Wu and Chao Dong and Liang Lin and Yu Qiao and Chen Change Loy and Woong Bae and Jaejun Yoo and Yoseob Han and Jong Chul Ye and Jae-Seok Choi and Munchurl Kim and Yuchen Fan and Jiahui Yu and Wei Han and Ding Liu and Haichao Yu and Zhangyang Wang and Honghui Shi and Xinchao Wang and Thomas S. Huang and Yunjin Chen and Kai Zhang and Wangmeng Zuo and Zhimin Tang and Linkai Luo and Shaohui Li and Min Fu and Lei Cao and Wen Heng and Giang Bui and Truc Le and Ye Duan and Dacheng Tao and Ruxin Wang and Xu Lin and Jianxin Pang and Jinchang Xu and Yu Zhao and Xiangyu Xu and Jinshan Pan and Deqing Sun and Yujin Zhang and Xibin Song and Yuchao Dai and Xueying Qin and Xuan-Phung Huynh and Tiantong Guo and Hojjat Seyed Mousavi and Tiep Huu Vu and Vishal Monga and Cristovao Cruz and Karen Egiazarian and Vladimir Katkovnik and Rakesh Mehta and Arnav Kumar Jain and Abhinav Agarwalla and Ch V Sai Praveen and Ruofan Zhou and Hongdiao Wen and Che Zhu and Zhiqiang Xia and Zhengtao Wang and Qi Guo},
  title = {NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017) Workshops},
  year = {2017},
  month = {July},
  keywords = {}
}