NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results

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 usin...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Bhat, Goutam, Danelljan, Martin, Timofte, Radu, Akita, Kazutoshi, Cho, Wooyeong, Fan, Haoqiang, Jia, Lanpeng, Kim, Daeshik, Lecouat, Bruno, Li, Youwei, Liu, Shuaicheng, Liu, Ziluan, Luo, Ziwei, Maeda, Takahiro, Mairal, Julien, Micheloni, Christian, Mo, Xuan, Oba, Takeru, Ostyakov, Pavel, Ponce, Jean, Son, Sanghyeok, Sun, Jian, Ukita, Norimichi, Rao, Muhammad Umer, Yan, Youliang, Yu, Lei, Zhussip, Magauiya, Zou, Xueyi
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 07.06.2021
Subjects
Computer Science - Computer Vision and Pattern Recognition
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2106.03839