NTIRE 2022 Burst Super-Resolution Challenge

• Published in: 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2022) pp. 1040 - 1060
• Main Authors: Bhat, Goutam, Danelljan, Martin, Timofte, Radu, Cao, Yizhen, Cao, Yuntian, Chen, Meiya, Chen, Xihao, Cheng, Shen, Dudhane, Akshay, Fan, Haoqiang, Gang, Ruipeng, Gao, Jian, Gu, Yan, Huang, Jie, Huang, Liufeng, Jo, Youngsu, Kang, Sukju, Khan, Salman, Shahbaz Khan, Fahad, Kondo, Yuki, Li, Chenghua, Li, Fangya, Li, Jinjing, Li, Youwei, Li, Zechao, Liu, Chenming, Liu, Shuaicheng, Liu, Zikun, Liu, Zhuoming, Luo, Ziwei, Luo, Zhengxiong, Mehta, Nancy, Murala, Subrahmanyam, Nam, Yoonchan, Nakatani, Chihiro, Ostyakov, Pavel, Pan, Jinshan, Song, Ge, Sun, Jian, Sun, Long, Tang, Jinhui, Ukita, Norimichi, Wen, Zhihong, Wu, Qi, Wu, Xiaohe, Xiao, Zeyu, Xiong, Zhiwei, Xu, Rongjian, Xu, Ruikang, Yan, Youliang, Yang, Jialin, Yang, Wentao, Yang, Zhongbao, Yasue, Fuma, Yao, Mingde, Yu, Lei, Zhang, Cong, Waqas Zamir, Syed, Zhang, Jianxing, Zhang, Shuohao, Zhang, Zhilu, Zheng, Qian, Zhou, Gaofeng, Zhussip, Magauiya, Zou, Xueyi, Zuo, Wangmeng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-06-2022
• Subjects: Network architecture; Noise reduction; Pattern recognition; Photography; Superresolution; Training; Transformers
• ISBN: 9781665487405; 1665487402; 1665487399; 9781665487399
• ISSN: 2160-7516
• DOI: 10.1109/CVPRW56347.2022.00117

Burst super-resolution has received increased attention in recent years due to its applications in mobile photography. By merging information from multiple shifted images of a scene, burst super-resolution aims to recover details which otherwise cannot be obtained using a simple input image. This paper reviews the NTIRE 2022 challenge on burst super-resolution. In the challenge, the participants were tasked with generating a clean RGB image with 4× higher resolution, given a RAW noisy burst as input. That is, the methods need to perform joint denoising, demosaicking, and super-resolution. The challenge consisted of 2 tracks. Track 1 employed synthetic data, where pixel-accurate high-resolution ground truths are available. Track 2 on the other hand used real-world bursts captured from a handheld camera, along with approximately aligned reference images captured using a DSLR. 14 teams participated in the final testing phase. The top performing methods establish a new state-of-the-art on the burst super-resolution task.