1. NTIRE 2019 Challenge on Real Image Super-Resolution: Methods and Results
- Author
-
Furui Bai, Jiawei Li, Sun Anshun, Fujie Gao, Yajun Qiu, Lei Liu, Xiumei Wang, Jiye Liu, Jing Liu, Lei Zhang, Jinghui Qin, Sanghoon Yoon, Guoan Cheng, Ruicheng Feng, Zheng Hui, Lin Zha, Li Guo, Dongliang He, Chu-Tak Li, Cuihua Li, Guochen Xie, Jun Yu, Rong Chen, Bowen Li, Shuhang Gu, Wenyi Tang, Shu Zhan, Zhang Yumei, Xiaoyun Jiang, Yanyun Qu, Qingwen He, Pengxu Wei, Ze Pan, Sungho Kim, Pablo Navarrete Michelini, Zhengping Wei, Xuan Xu, Darui Li, Peidong He, Minbeom Kim, Fan Hongfei, Joon-Soo Kim, Liang Lin, Changyeop Shin, Leilei Zhu, Xiang Li, Wangmeng Zuo, Jianrui Cai, Ling Shao, Donghee Son, Qunbo Lv, Yongcheng Jing, Can Zhao, Yi Fu, Yu Qiao, Chung-Chi Tsai, Shilei Wen, Dongwon Park, Xin Li, Zhi-Song Liu, Li-Wen Wang, Yuanfei Huang, Hongzhi Zhang, Jingdong Liu, Xiaotong Luo, Chen Hong, Fahad Shahbaz Khan, Zewei He, Chao Dong, Pengju Liu, Se Young Chun, Zheng Tan, Yanpeng Cao, Joon-Hee Choi, Chao Li, Xiaopeng Sun, Syed Waqas Zamir, Kai Zhang, Hong Cai, Youngjung Kim, Qiuyu Li, Radu Timofte, Ai Matsune, Yukai Shi, Xiao Liu, Wen Lu, Salman H. Khan, Mengyan Li, Wushao Wen, Huaijuan Zang, Mingli Song, Junhyung Kwak, Shang-Chih Chuang, Hanwen Liu, Xinbo Gao, Du Chen, Ding Yukang, Siliang Tang, Aditya Arora, Zhang Wenjie, Lishan Huang, Jinjin Gu, Ruxin wang, and Dan Zhu
- Subjects
business.industry ,Computer science ,Track (disk drive) ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,020206 networking & telecommunications ,02 engineering and technology ,Real image ,Scale factor ,Superresolution ,Image (mathematics) ,0202 electrical engineering, electronic engineering, information engineering ,Focal length ,020201 artificial intelligence & image processing ,Computer vision ,Artificial intelligence ,business ,Focus (optics) ,Image resolution ,Image restoration - Abstract
This paper reviewed the 3rd NTIRE challenge on single-image super-resolution (restoration of rich details in a low-resolution image) with a focus on proposed solutions and results. The challenge had 1 track, which was aimed at the real-world single image super-resolution problem with an unknown scaling factor. Participants were mapping low-resolution images captured by a DSLR camera with a shorter focal length to their high-resolution images captured at a longer focal length. With this challenge, we introduced a novel real-world super-resolution dataset (RealSR). The track had 403 registered participants, and 36 teams competed in the final testing phase. They gauge the state-of-the-art in real-world single image super-resolution.
- Published
- 2019
- Full Text
- View/download PDF