Cover Image

Saved in:
Bibliographic Details
Main Authors: 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
Format: Preprint
Published: 2026
Subjects:
Computer Vision and Pattern Recognition
Online Access:https://arxiv.org/abs/2604.10532
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of 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.

Similar Items