NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results-猫眼课题宝

DOI：

10.1109/cvprw56347.2022.00118

发表时间：

2022-05

期刊：

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Yawei Li;K. Zhang;R. Timofte;L. Gool;F. Kong;Ming-xing Li;Songwei Liu;Zongcai Du;Ding Liu;Chenhui Zhou;Jingyi Chen;Qingrui Han;Zheyuan Li;Yingqi Liu;Xiangyu Chen;Haoming Cai;Yuanjiao Qiao;Chao Dong;Long Sun;Jin-shan Pan;Yi Zhu;Zhikai Zong;Xiaoxiao Liu;Zheng Hui;Tao Yang;Peiran Ren;Xuansong Xie;Xiansheng Hua;Yanbo Wang;Xiaozhong Ji;Chuming Lin;Donghao Luo;Ying Tai;Chengjie Wang;Zhizhong Zhang;Yuan Xie;Shen Cheng;Ziwei Luo;Lei Yu;Zhi-hong Wen;Qi Wu1;Youwei Li;Haoqiang Fan;Jian Sun;Shuaicheng Liu;Yuanfei Huang;Meiguang Jin;Huan Huang;Jing Liu;Xinjian Zhang;Yan Wang;L. Long;Gen Li;Yuanfan Zhang-;Zuo-yuan Cao;Lei Sun;Panaetov Alexander;Yucong Wang;Mi Cai;Li Wang;Lu Tian;Zheyuan Wang;H. Ma;Jie Liu-;Chao Chen;Y. Cai;Jie Tang;Gang Wu;Weiran Wang;Shi-Cai Huang;Honglei Lu;Huan Liu;Keyan Wang;Jun Chen-;Shi Chen;Yu-Hsuan Miao;Zimo Huang;L. Zhang;Mustafa Ayazouglu;Wei Xiong;Chengyi Xiong;Fei Wang;Hao Li;Rui Wen;Zhi-Hao Yang;Wenbin Zou;W. Zheng;Tian-Chun Ye;Yuncheng Zhang;Xiangzhen Kong;Aditya Arora;Syed Waqas Zamir;Salman H. Khan;Munawar Hayat;F. Khan;Dan Ning;Jing Tang;Han Huang;Yufei Wang;Z. Peng;Hao-Wen Li;Wenxue Guan;Sheng-rong Gong;Xin Li;Jun Liu;Wanjun Wang;Deng-Guang Zhou;Kun Zeng;Han-Yuan Lin;Xinyu Chen;Jin-Tao Fang

本文回顾了2022年NTIRE关于高效单图像超分辨率的挑战赛，重点关注所提出的解决方案和结果。挑战赛的任务是基于低分辨率和相应高分辨率图像对，将输入图像以×4的放大倍数进行超分辨率处理。目的是设计一种用于单图像超分辨率的网络，该网络根据包括运行时间、参数、浮点运算次数（FLOPs）、激活值和内存消耗在内的多个指标来提高效率，同时在DIV2K验证集上至少保持29.00dB的峰值信噪比（PSNR）。将信息多蒸馏网络（IMDN）设定为效率测量的基线。该挑战赛有3个赛道，包括主赛道（运行时间）、子赛道一（模型复杂度）和子赛道二（综合性能）。在主赛道中，对参赛作品的实际运行时间性能进行了评估。参赛队伍的排名直接由验证集和测试集上平均运行时间的绝对值决定。在子赛道一中，考虑了参数数量和浮点运算次数。并且将这两个指标的单独排名相加，以确定该赛道的最终排名。在子赛道二中，考虑了挑战赛描述中提到的所有五个指标，包括运行时间、参数数量、浮点运算次数、激活值和内存消耗。与子赛道一类似，将五个指标的排名相加以确定最终排名。该挑战赛有303名注册参与者，43个团队提交了有效作品。它们衡量了高效单图像超分辨率的最新技术水平。

This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution.

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

文献摘要

被引文献

相似文献