NTIRE 2022挑战有效的超分辨率：方法和结果

论文标题

NTIRE 2022挑战有效的超分辨率：方法和结果

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

论文作者

Li, Yawei, Zhang, Kai, Timofte, Radu, Van Gool, Luc, Kong, Fangyuan, Li, Mingxi, Liu, Songwei, Du, Zongcai, Liu, Ding, Zhou, Chenhui, Chen, Jingyi, Han, Qingrui, Li, Zheyuan, Liu, Yingqi, Chen, Xiangyu, Cai, Haoming, Qiao, Yu, Dong, Chao, Sun, Long, Pan, Jinshan, Zhu, Yi, Zong, Zhikai, Liu, Xiaoxiao, Hui, Zheng, Yang, Tao, Ren, Peiran, Xie, Xuansong, Hua, Xian-Sheng, Wang, Yanbo, Ji, Xiaozhong, Lin, Chuming, Luo, Donghao, Tai, Ying, Wang, Chengjie, Zhang, Zhizhong, Xie, Yuan, Cheng, Shen, Luo, Ziwei, Yu, Lei, Wen, Zhihong, Wu1, Qi, Li, Youwei, Fan, Haoqiang, Sun, Jian, Liu, Shuaicheng, Huang, Yuanfei, Jin, Meiguang, Huang, Hua, Liu, Jing, Zhang, Xinjian, Wang, Yan, Long, Lingshun, Li, Gen, Zhang, Yuanfan, Cao, Zuowei, Sun, Lei, Alexander, Panaetov, Wang, Yucong, Cai, Minjie, Wang, Li, Tian, Lu, Wang, Zheyuan, Ma, Hongbing, Liu, Jie, Chen, Chao, Cai, Yidong, Tang, Jie, Wu, Gangshan, Wang, Weiran, Huang, Shirui, Lu, Honglei, Liu, Huan, Wang, Keyan, Chen, Jun, Chen, Shi, Miao, Yuchun, Huang, Zimo, Zhang, Lefei, Ayazoğlu, Mustafa, Xiong, Wei, Xiong, Chengyi, Wang, Fei, Li, Hao, Wen, Ruimian, Yang, Zhijing, Zou, Wenbin, Zheng, Weixin, Ye, Tian, Zhang, Yuncheng, Kong, Xiangzhen, Arora, Aditya, Zamir, Syed Waqas, Khan, Salman, Hayat, Munawar, Khan, Fahad Shahbaz, Ning, Dandan Gaoand Dengwen Zhouand Qian, Tang, Jingzhu, Huang, Han, Wang, Yufei, Peng, Zhangheng, Li, Haobo, Guan, Wenxue, Gong, Shenghua, Li, Xin, Liu, Jun, Wang, Wanjun, Zhou, Dengwen, Zeng, Kun, Lin, Hanjiang, Chen, Xinyu, Fang, Jinsheng

论文摘要

本文回顾了NTIRE 2022对有效的单图像超分辨率的挑战，重点是拟议的解决方案和结果。挑战的任务是基于低和相应的高分辨率图像对$ \ times $ 4的放大系数$ \ times $ 4的超级溶解输入图像。目的是设计一个用于单图超分辨率的网络，该网络根据几个指标，包括运行时，参数，拖失板，激活和内存消耗来提高效率，同时至少在DIV2K验证集上保持29.00DB的PSNR。 IMDN被视为效率测量的基线。挑战有3条轨道，包括主轨道（运行时），子轨道一（模型复杂性）和子轨道2（总体性能）。在主要曲目中，评估了提交的实际运行时性能。团队的排名直接取决于验证集和测试集中平均运行时的绝对值。在子轨道上，考虑了参数和拖鞋的数量。总结了两个指标的个别排名，以确定此曲目中的最终排名。在子轨道的两个中，考虑了挑战描述中提到的所有五个指标，包括运行时，参数计数，拖失板，激活和记忆消耗。与子跟踪相似，概括了五个指标的排名以确定最终排名。挑战有303名注册参与者，有43个团队提交了有效的提交。他们在有效的单图像超分辨率中评估了最新的。

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 $\times$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.

下载PDF全文

下载文献需遵守相关版权规定

论文标题