加载中…
2020-05-03
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
Kai ZhangShuhang GuRadu TimofteTaizhang ShangQiuju DaiShengchen ZhuTong YangYandong GuoYounghyun JoSejong YangSeon Joo KimLin ZhaJiande JiangXinbo GaoWen LuJing LiuKwangjin YoonTaegyun JeonKazutoshi AkitaTakeru OobaNorimichi UkitaZhipeng LuoYuehan YaoZhenyu XuDongliang HeWenhao WuYukang DingChao LiFu LiShilei WenJianwei LiFuzhi YangHuan YangJianlong FuByung-Hoon KimJaeHyun BaekJong Chul YeYuchen FanThomas S. HuangJunyeop LeeBokyeung LeeJungki MinGwantae KimKanghyu LeeJaihyun ParkMykola MykhailychHaoyu ZhongYukai ShiXiaojun YangZhijing YangLiang LinTongtong ZhaoJinjia PengHuibing WangZhi JinJiahao WuYifu ChenChenming ShangHuanrong ZhangJeongki MinHrishikesh P SDensen PuthusseryJiji C V
文献摘要
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor 16 based on a set of prior examples of low and corresponding high resolution images. The goal is to obtain a network design capable to produce high resolution results with the best perceptual quality and similar to the ground truth. The track had 280 registered participants, and 19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.
讨论
0讲解博客
生成讲解博客的中文版本
AI智能校验
生成AI智能校验的中文版本