NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results

Chen, Zheng; Wang, Jingkai; Liu, Kai; Gong, Jue; Sun, Lei; Wu, Zongwei; Timofte, Radu; Zhang, Yulun; Zhang, Jianxing; Wu, Jinlong; Wang, Jun; Xie, Zheng; Jeon, Hakjae; Han, Suejin; Chun, Hyung-Ju; Park, Hyunhee; Yin, Zhicun; Chen, Junjie; Liu, Ming; Li, Xiaoming; Zhou, Chao; Zuo, Wangmeng; Zhang, Weixia; Li, Dingquan; Ma, Kede; Zhang, Yun; Zheng, Zhuofan; Liu, Yuyue; Tang, Shizhen; Zhang, Zihao; Ning, Yi; Jiang, Hao; An, Wenjie; Yu, Kangmeng; Wang, Chenyang; Jiang, Kui; Liu, Xianming; Jiang, Junjun; Zhang, Yingfu; He, Gang; Wang, Siqi; Xu, Kepeng; Liu, Zhenyang; Zhou, Changxin; Shen, Shanlan; Duan, Yubo; Chen, Yiang; Guo, Jin; Yang, Mengru; Lee, Jen-Wei; Lee, Chia-Ming; Hsu, Chih-Chung; Peng, Hu; He, Chunming

Zheng Chen, Jingkai Wang, Kai Liu, Jue Gong, Lei Sun, Zongwei Wu, Radu Timofte, Yulun Zhang, Jianxing Zhang, Jinlong Wu, Jun Wang, Zheng Xie, Hakjae Jeon, Suejin Han, Hyung-Ju Chun, Hyunhee Park, Zhicun Yin, Junjie Chen, Ming Liu, Xiaoming Li, Chao Zhou, Wangmeng Zuo, Weixia Zhang, Dingquan Li, Kede Ma, Yun Zhang, Zhuofan Zheng, Yuyue Liu, Shizhen Tang, Zihao Zhang, Yi Ning, Hao Jiang, Wenjie An, Kangmeng Yu, Chenyang Wang, Kui Jiang, Xianming Liu, Junjun Jiang, Yingfu Zhang, Gang He, Siqi Wang, Kepeng Xu, Zhenyang Liu, Changxin Zhou, Shanlan Shen, Yubo Duan, Yiang Chen, Jin Guo, Mengru Yang, Jen-Wei Lee, Chia-Ming Lee, Chih-Chung Hsu, Hu Peng, Chunming He; Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops, 2025, pp. 1536-1547

Abstract

This paper provides a review of the NTIRE 2025 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural, realistic outputs while maintaining identity consistency. Its goal is to advance state-of-the-art solutions for perceptual quality and realism, without imposing constraints on computational resources or training data. The track of the challenge evaluates performance using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 141 registrants, with 13 teams submitting valid models, and ultimately, 10 teams achieved a valid score in the final ranking. This collaborative effort advances the performance of real-world face restoration while offering an in-depth overview of the latest trends in the field.

Related Material

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2025_CVPR, author = {Chen, Zheng and Wang, Jingkai and Liu, Kai and Gong, Jue and Sun, Lei and Wu, Zongwei and Timofte, Radu and Zhang, Yulun and Zhang, Jianxing and Wu, Jinlong and Wang, Jun and Xie, Zheng and Jeon, Hakjae and Han, Suejin and Chun, Hyung-Ju and Park, Hyunhee and Yin, Zhicun and Chen, Junjie and Liu, Ming and Li, Xiaoming and Zhou, Chao and Zuo, Wangmeng and Zhang, Weixia and Li, Dingquan and Ma, Kede and Zhang, Yun and Zheng, Zhuofan and Liu, Yuyue and Tang, Shizhen and Zhang, Zihao and Ning, Yi and Jiang, Hao and An, Wenjie and Yu, Kangmeng and Wang, Chenyang and Jiang, Kui and Liu, Xianming and Jiang, Junjun and Zhang, Yingfu and He, Gang and Wang, Siqi and Xu, Kepeng and Liu, Zhenyang and Zhou, Changxin and Shen, Shanlan and Duan, Yubo and Chen, Yiang and Guo, Jin and Yang, Mengru and Lee, Jen-Wei and Lee, Chia-Ming and Hsu, Chih-Chung and Peng, Hu and He, Chunming}, title = {NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {1536-1547} }