NTIRE 2021 Learning the Super-Resolution Space Challenge
Andreas Lugmayr, Martin Danelljan, Radu Timofte, Christoph Busch, Yang Chen, Jian Cheng, Vishal Chudasama, Ruipeng Gang, Shangqi Gao, Kun Gao, Laiyun Gong, Qingrui Han, Chao Huang, Zhi Jin, Younghyun Jo, Seon Joo Kim, Young-Geun Kim, Seung-Jun Lee, Yuchen Lei, Chu-Tak Li, Chenghua Li, Ke Li, Zhi-Song Liu, Youming Liu, Nan Nan, Seung-Ho Park, Heena Patel, Shichong Peng, Kalpesh Prajapati, Haoran Qi, Kiran Raja, Raghavendra Ramachandra, Wan-Chi Siu, Donghee Son, Ruixia Song, Kishor Upla, Liwen Wang, Yatian Wang, Junwei Wang, Qianyu Wu, XU Xin-hua, Sejong Yang, Zhen Yuan, Liting Zhang, Huanrong Zhang, Junkai Zhang, Yifan Zhang, Zhenzhou Zhang, Hangqi Zhou, Aichun Zhu, Xiahai Zhuang, Jiaxin Zou
Abstract
This paper reviews the NTIRE 2021 challenge on learning the super-Resolution space. It focuses on the participating methods and final results. The challenge addresses the problem of learning a model capable of predicting the space of plausible super-resolution (SR) images, from a single low-resolution image. The model must thus be capable of sampling diverse outputs, rather than just generating a single SR image. The goal of the challenge is to spur research into developing learning formulations and models better suited for the highly ill-posed SR problem. And thereby advance the state-of-the-art in the broader SR field. In order to evaluate the quality of the predicted SR space, we propose a new evaluation metric and perform a comprehensive analysis of the participating methods. The challenge contains two tracks: 4× and 8 scale factor. In total, 11 teams competed in the final testing× phase.