计算机科学
人工智能
任务(项目管理)
分辨率(逻辑)
磁道(磁盘驱动器)
集合(抽象数据类型)
计算机视觉
图像分辨率
RGB颜色模型
数据集
图像(数学)
模式识别(心理学)
工程类
系统工程
操作系统
程序设计语言
作者
Goutam Bhat,Martin Danelljan,Radu Timofte,Kazutoshi Akita,Wooyeong Cho,Haoqiang Fan,Lanpeng Jia,Dae‐Shik Kim,Bruno Lecouat,Youwei Li,Shuaicheng Liu,Ziluan Liu,Ziwei Luo,Takahiro Maeda,Julien Mairal,Christian Micheloni,Xuan Mo,Takeru Oba,Pavel Ostyakov,Jean Ponce
标识
DOI:10.1109/cvprw53098.2021.00073
摘要
This paper reviews the NTIRE2021 challenge on burst super-resolution. Given a RAW noisy burst as input, the task in the challenge was to generate a clean RGB image with 4 times higher resolution. The challenge contained two tracks; Track 1 evaluating on synthetically generated data, and Track 2 using real-world bursts from mobile camera. In the final testing phase, 6 teams submitted results using a diverse set of solutions. The top-performing methods set a new state-of-the-art for the burst super-resolution task.
科研通智能强力驱动
Strongly Powered by AbleSci AI