학술논문
Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey
Document Type
Working Paper
Author
Conde, Marcos V.; Vasluianu, Florin-Alexandru; Timofte, Radu; Zhang, Jianxing; Li, Jia; Wang, Fan; Li, Xiaopeng; Liu, Zikun; Park, Hyunhee; Song, Sejun; Kim, Changho; Huang, Zhijuan; Yu, Hongyuan; Wan, Cheng; Xiang, Wending; Lin, Jiamin; Zhong, Hang; Zhang, Qiaosong; Sun, Yue; Yin, Xuanwu; Zuo, Kunlong; Xu, Senyan; Jiang, Siyuan; Sun, Zhijing; Zhu, Jiaying; Li, Liangyan; Chen, Ke; Li, Yunzhe; Ning, Yimo; Zhao, Guanhua; Chen, Jun; Yu, Jinyang; Xu, Kele; Xu, Qisheng; Dou, Yong
Source
Subject
Language
Abstract
This paper reviews the NTIRE 2024 RAW Image Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. Th goal of this challenge is to upscale RAW Bayer images by 2x, considering unknown degradations such as noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. The performance of the top-5 submissions is reviewed and provided here as a gauge for the current state-of-the-art in RAW Image Super-Resolution.
Comment: CVPR 2024 - NTIRE Workshop
Comment: CVPR 2024 - NTIRE Workshop