Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.10532 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917410434449408 |
|---|---|
| author | Wang, Jingkai Gong, Jue Chen, Zheng Liu, Kai Li, Jiatong Zhang, Yulun Timofte, Radu Tu, Jiachen Shi, Yaokun Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Chen, Yingsi Liu, Yijiao Li, Hui Wang, Yu Zhu, Congchao Lefterache, Alexandru-Gabriel Radoi, Anamaria Yan, Chuanyue Lu, Tao Zhang, Yanduo Zhao, Kanghui Wang, Jiaming Li, Yuqi Xiong, WenBo Chen, Yifei Hu, Xian Deng, Wei Zhou, Daiguo Roy V, Sujith Jesuraj, Claudia B, Vikas LC, Spoorthi Akalwadi, Nikhil Tabib, Ramesh Ashok Mudenagudi, Uma Jiang, Yuxuan Zeng, Chengxi Peng, Tianhao Zhang, Fan Zhou, David Bull Wei Li, Linfeng Huang, Hongyu Lee, Hoyoung Oh, SangYun Jeong, ChangYoung Niu, Axi Zhang, Jinyang Wu, Zhenguo Qing, Senyan Sun, Jinqiu Zhang, Yanning |
| author_facet | Wang, Jingkai Gong, Jue Chen, Zheng Liu, Kai Li, Jiatong Zhang, Yulun Timofte, Radu Tu, Jiachen Shi, Yaokun Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Chen, Yingsi Liu, Yijiao Li, Hui Wang, Yu Zhu, Congchao Lefterache, Alexandru-Gabriel Radoi, Anamaria Yan, Chuanyue Lu, Tao Zhang, Yanduo Zhao, Kanghui Wang, Jiaming Li, Yuqi Xiong, WenBo Chen, Yifei Hu, Xian Deng, Wei Zhou, Daiguo Roy V, Sujith Jesuraj, Claudia B, Vikas LC, Spoorthi Akalwadi, Nikhil Tabib, Ramesh Ashok Mudenagudi, Uma Jiang, Yuxuan Zeng, Chengxi Peng, Tianhao Zhang, Fan Zhou, David Bull Wei Li, Linfeng Huang, Hongyu Lee, Hoyoung Oh, SangYun Jeong, ChangYoung Niu, Axi Zhang, Jinyang Wu, Zhenguo Qing, Senyan Sun, Jinqiu Zhang, Yanning |
| contents | This paper provides a review of the NTIRE 2026 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural and 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. Performance is evaluated using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 96 registrants, with 10 teams submitting valid models; ultimately, 9 teams achieved valid scores 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10532 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results Wang, Jingkai Gong, Jue Chen, Zheng Liu, Kai Li, Jiatong Zhang, Yulun Timofte, Radu Tu, Jiachen Shi, Yaokun Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Chen, Yingsi Liu, Yijiao Li, Hui Wang, Yu Zhu, Congchao Lefterache, Alexandru-Gabriel Radoi, Anamaria Yan, Chuanyue Lu, Tao Zhang, Yanduo Zhao, Kanghui Wang, Jiaming Li, Yuqi Xiong, WenBo Chen, Yifei Hu, Xian Deng, Wei Zhou, Daiguo Roy V, Sujith Jesuraj, Claudia B, Vikas LC, Spoorthi Akalwadi, Nikhil Tabib, Ramesh Ashok Mudenagudi, Uma Jiang, Yuxuan Zeng, Chengxi Peng, Tianhao Zhang, Fan Zhou, David Bull Wei Li, Linfeng Huang, Hongyu Lee, Hoyoung Oh, SangYun Jeong, ChangYoung Niu, Axi Zhang, Jinyang Wu, Zhenguo Qing, Senyan Sun, Jinqiu Zhang, Yanning Computer Vision and Pattern Recognition This paper provides a review of the NTIRE 2026 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural and 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. Performance is evaluated using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 96 registrants, with 10 teams submitting valid models; ultimately, 9 teams achieved valid scores 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. |
| title | The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.10532 |