This paper reviews the NTIRE 2025 RAW Image Restoration and Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Restoration and Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. The goal of this challenge is two fold, (i) restore RAW images with blur and noise degradations, (ii) upscale RAW Bayer images by 2x, considering unknown noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. This report presents the current state-of-the-art in RAW Restoration.

View on arXiv

@article{conde2025_2506.02197,
  title={ NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution },
  author={ Marcos V. Conde and Radu Timofte and Zihao Lu and Xiangyu Kong and Xiaoxia Xing and Fan Wang and Suejin Han and MinKyu Park and Tianyu Zhang and Xin Luo and Yeda Chen and Dong Liu and Li Pang and Yuhang Yang and Hongzhong Wang and Xiangyong Cao and Ruixuan Jiang and Senyan Xu and Siyuan Jiang and Xueyang Fu and Zheng-Jun Zha and Tianyu Hao and Yuhong He and Ruoqi Li and Yueqi Yang and Xiang Yu and Guanlan Hong and Minmin Yi and Yuanjia Chen and Liwen Zhang and Zijie Jin and Cheng Li and Lian Liu and Wei Song and Heng Sun and Yubo Wang and Jinghua Wang and Jiajie Lu and Watchara Ruangsan },
  journal={arXiv preprint arXiv:2506.02197},
  year={ 2025 }
}

Comments on this paper