ML Anthology

NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results

Andreas Lugmayr, Martin Danelljan, Radu Timofte, Namhyuk Ahn, Dongwoon Bai, Jie Cai, Yun Cao, Junyang Chen, Kaihua Cheng, Se Young Chun, Wei Deng, Mostafa El-Khamy, Chiu Man Ho, Xiaozhong Ji, Amin Kheradmand, Gwantae Kim, Hanseok Ko, Kanghyu Lee, Jungwon Lee, Hao Li, Ziluan Liu, Zhi-Song Liu, Shuai Liu, Yunhua Lu, Zibo Meng, Pablo Navarrete Michelini, Christian Micheloni, Kalpesh Prajapati, Haoyu Ren, Yonghyeok Seo, Wan-Chi Siu, Kyung-Ah Sohn, Ying Tai, Rao Muhammad Umer, Shuangquan Wang, Huibing Wang, Timothy Haoning Wu, Haoning Wu, Biao Yang, Fuzhi Yang, Jaejun Yoo, Tongtong Zhao, Yuanbo Zhou, Haijie Zhuo, Ziyao Zong, Xueyi Zou
CVPRW 2020 pp. 2058-2076
doi:10.1109/CVPRW50498.2020.00255 /cvprw/2020/lugmayr2020cvprw-ntire/

Abstract

This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable. For training, only one set of source input images is therefore provided along with a set of unpaired high-quality target images. In Track 1: Image Processing artifacts, the aim is to super-resolve images with synthetically generated image processing artifacts. This allows for quantitative benchmarking of the approaches w.r.t. a ground-truth image. In Track 2: Smartphone Images, real low-quality smart phone images have to be super-resolved. In both tracks, the ultimate goal is to achieve the best perceptual quality, evaluated using a human study. This is the second challenge on the subject, following AIM 2019, targeting to advance the state-of-the-art in super-resolution. To measure the performance we use the benchmark protocol from AIM 2019. In total 22 teams competed in the final testing phase, demonstrating new and innovative solutions to the problem.

PDF CVPRW Semantic Scholar

Cite

Text

Lugmayr et al. "NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00255

Markdown

[Lugmayr et al. "NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/lugmayr2020cvprw-ntire/) doi:10.1109/CVPRW50498.2020.00255

BibTeX

@inproceedings{lugmayr2020cvprw-ntire,
  title     = {{NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results}},
  author    = {Lugmayr, Andreas and Danelljan, Martin and Timofte, Radu and Ahn, Namhyuk and Bai, Dongwoon and Cai, Jie and Cao, Yun and Chen, Junyang and Cheng, Kaihua and Chun, Se Young and Deng, Wei and El-Khamy, Mostafa and Ho, Chiu Man and Ji, Xiaozhong and Kheradmand, Amin and Kim, Gwantae and Ko, Hanseok and Lee, Kanghyu and Lee, Jungwon and Li, Hao and Liu, Ziluan and Liu, Zhi-Song and Liu, Shuai and Lu, Yunhua and Meng, Zibo and Michelini, Pablo Navarrete and Micheloni, Christian and Prajapati, Kalpesh and Ren, Haoyu and Seo, Yonghyeok and Siu, Wan-Chi and Sohn, Kyung-Ah and Tai, Ying and Umer, Rao Muhammad and Wang, Shuangquan and Wang, Huibing and Wu, Timothy Haoning and Wu, Haoning and Yang, Biao and Yang, Fuzhi and Yoo, Jaejun and Zhao, Tongtong and Zhou, Yuanbo and Zhuo, Haijie and Zong, Ziyao and Zou, Xueyi},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2020},
  pages     = {2058-2076},
  doi       = {10.1109/CVPRW50498.2020.00255},
  url       = {https://mlanthology.org/cvprw/2020/lugmayr2020cvprw-ntire/}
}