NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results. Yawei Li , Yulun Zhang , Radu Timofte , Luc Van Gool , Lei Yu , Youwei Li , Xinpeng Li , Ting Jiang , Qi Wu , Mingyan Han , Wenjie Lin , Chengzhi Jiang , Jinting Luo , Haoqiang Fan , Shuaicheng Liu , Yucong Wang , Minjie Cai , Mingxi Li , Yuhang Zhang , Xianjun Fan , Yankai Sheng , Yanyu Mao , Nihao Zhang , Qian Wang , Mingjun Zheng , Long Sun , Jinshan Pan , Jiangxin Dong , Jinhui Tang , Zhongbao Yang , Yan Wang , Erlin Pan , Qixuan Cai , Xinan Dai , Magauiya Zhussip , Nikolay Kalyazin , Dmitry Vyal , Xueyi Zou , Youliang Yan , Heaseo Chung , Jin Zhang , Gaocheng Yu , Feng Zhang , Hongbin Wang , Bohao Liao , Zhibo Du , Yu-Liang Wu , Gege Shi , Long Peng , Yang Wang , Yang Cao , Zhengjun Zha , Zhi-Kai Huang , Yi-Chung Chen , Yuan-Chun Chiang , Hao-Hsiang Yang , Wei-Ting Chen , Hua-En Chang , I-Hsiang Chen , Chia-Hsuan Hsieh , Sy-Yen Kuo , Xin Liu , Jiahao Pan , Hongyuan Yu , Weichen Yu , Lin Ge , Jiahua Dong , Yajun Zou , Zhuoyuan Wu , Binnan Han , Xiaolin Zhang , Heng Zhang , Xuanwu Yin , Kunlong Zuo , Weijian Deng , Hongjie Yuan , Zengtong Lu , Mingyu Ouyang , Wenzhuo Ma , Nian Liu , Hanyou Zheng , Yuantong Zhang , Junxi Zhang , Zhenzhong Chen , Garas Gendy , Nabil Sabor , Jingchao Hou , Guanghui He , Yurui Zhu , Xi Wang , Xueyang Fu , Zheng-Jun Zha , Daheng Yin , Mengyang Liu , Baijun Chen , Ao Li , Lei Luo , Kangjun Jin , Ce Zhu , Xiaoming Zhang , Chengxing Xie , Linze Li , Haiteng Meng , Tianlin Zhang , Tianrui Li , Xiaole Zhao , Zhao Zhang , Baiang Li , Huan Zheng , Suiyi Zhao , Yangcheng Gao , Jiahuan Ren , Kang Hu , Jingpeng Shi , Zhijian Wu , Dingjiang Huang , Jinchen Zhu , Hui Li , Qianru Xv , Tianle Liu , Gang Wu , Junpeng Jiang , Xianming Liu , Junjun Jiang , Mingjian Zhang , Shizhuang Weng , Jing Hu , Chengxu Wu , Qinrui Fan , Chengming Feng , Ziwei Luo , Shu Hu , Siwei Lyu , Xi Wu , Xin Wang CVPR Workshops（2023）
摘要
This paper reviews the NTIRE 2023 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects such as runtime, parameters, FLOPs, activations, memory footprint, and depth of RFDN while at least maintaining the PSNR of 29.00dB on DIV2K validation datasets. The challenge had 272 registered participants, and 35 teams made valid submissions. They gauge the state-of-the-art for efficient single-image super-resolution.
更多 查看译文
关键词
DIV2K validation datasets, FLOP, memory footprint, NTIRE 2023 challenge, PSNR, RDFN, registered participants, single-image super-resolution
AI 理解论文
溯源树
样例
