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

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

CVPRW 2017 pp. 1110-1121

doi:10.1109/CVPRW.2017.149 /cvprw/2017/timofte2017cvprw-ntire/

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.

PDF CVPRW Semantic Scholar

Cite

Text

Timofte et al. "NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.149

Markdown

[Timofte et al. "NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/timofte2017cvprw-ntire/) doi:10.1109/CVPRW.2017.149

BibTeX

@inproceedings{timofte2017cvprw-ntire,
  title     = {{NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results}},
  author    = {Timofte, Radu and Agustsson, Eirikur and Van Gool, Luc and Yang, Ming-Hsuan and Zhang, Lei and Lim, Bee and Son, Sanghyun and Kim, Heewon and Nah, Seungjun and Lee, Kyoung Mu and Wang, Xintao and Tian, Yapeng and Yu, Ke and Zhang, Yulun and Wu, Shixiang and Dong, Chao and Lin, Liang and Qiao, Yu and Loy, Chen Change and Bae, Woong and Yoo, Jaejun and Han, Yoseob and Ye, Jong Chul and Choi, Jae-Seok and Kim, Munchurl and Fan, Yuchen and Yu, Jiahui and Han, Wei and Liu, Ding and Yu, Haichao and Wang, Zhangyang and Shi, Honghui and Wang, Xinchao and Huang, Thomas S. and Chen, Yunjin and Zhang, Kai and Zuo, Wangmeng and Tang, Zhimin and Luo, Linkai and Li, Shaohui and Fu, Min and Cao, Lei and Heng, Wen and Bui, Giang and Le, Truc and Duan, Ye and Tao, Dacheng and Wang, Ruxin and Lin, Xu and Pang, Jianxin and Xu, Jinchang and Zhao, Yu and Xu, Xiangyu and Pan, Jin-shan and Sun, Deqing and Zhang, Yujin and Song, Xibin and Dai, Yuchao and Qin, Xueying and Huynh, Xuan-Phung and Guo, Tiantong and Mousavi, Hojjat Seyed and Vu, Tiep Huu and Monga, Vishal and Cruz, Cristóvão and Egiazarian, Karen O. and Katkovnik, Vladimir and Mehta, Rakesh and Jain, Arnav Kumar and Agarwalla, Abhinav and Praveen, Ch V. Sai and Zhou, Ruofan and Wen, Hongdiao and Zhu, Che and Xia, Zhiqiang and Wang, Zhengtao and Guo, Qi},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2017},
  pages     = {1110-1121},
  doi       = {10.1109/CVPRW.2017.149},
  url       = {https://mlanthology.org/cvprw/2017/timofte2017cvprw-ntire/}
}