-
[pdf]
[arXiv]
[bibtex]@InProceedings{Conde_2024_CVPR, author = {Conde, Marcos V. and Vasluianu, Florin-Alexandru and Timofte, Radu and Zhang, Jianxing and Li, Jia and Wang, Fan and Li, Xiaopeng and Liu, Zikun and Park, Hyunhee and Song, Sejun and Kim, Changho and Huang, Zhijuan and Yu, Hongyuan and Wan, Cheng and Xiang, Wending and Lin, Jiamin and Zhong, Hang and Zhang, Qiaosong and Sun, Yue and Yin, Xuanwu and Zuo, Kunlong and Xu, Senyan and Jiang, Siyuan and Sun, Zhijing and Zhu, Jiaying and Li, Liangyan and Chen, Ke and Li, Yunzhe and Ning, Yimo and Zhao, Guanhua and Chen, Jun and Yu, Jinyang and Xu, Kele and Xu, Qisheng and Dou, Yong}, title = {Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {6745-6759} }
Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey
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.
Related Material