Image de couverture de livre

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Guan, Ya-nan, Zhang, Shaonan, Guo, Hang, Wang, Yawen, Fan, Xinying, Zhuang, Tianqu, Liang, Jie, Zeng, Hui, Qin, Guanyi, Qu, Lishen, Dai, Tao, Xia, Shu-Tao, Zhang, Lei, Timofte, Radu, Chen, Bin, Zhou, Yuanbo, Wang, Hongwei, Gao, Qinquan, Tong, Tong, Qian, Yanxin, You, Lizhao, Cong, Jingru, Xiong, Lei, Zhu, Shuyuan, Zhong, Zhi-Qiang, Lv, Kan, Yang, Yang, Tang, Kailing, Zhang, Minjian, Lei, Zhipei, Xu, Zhe, Zhang, Liwen, Gou, Dingyong, Wu, Yanlin, Li, Cong, Cui, Xiaohui, Liu, Jiajia, Xu, Guoyi, Jiang, Yaoxin, Shi, Yaokun, Tu, Jiachen, Wang, Liqing, Li, Shihang, Zhang, Bo, Wang, Biao, Xu, Haiming, Long, Xiang, Liao, Xurui, Zhai, Yanqiao, Li, Haozhe, Shi, Shijun, Zhang, Jiangning, Liu, Yong, Hu, Kai, Xu, Jing, Zeng, Xianfang, Liu, Yuyang, Wei, Minchen
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

_version_	1866910124721831936
author	Guan, Ya-nan Zhang, Shaonan Guo, Hang Wang, Yawen Fan, Xinying Zhuang, Tianqu Liang, Jie Zeng, Hui Qin, Guanyi Qu, Lishen Dai, Tao Xia, Shu-Tao Zhang, Lei Timofte, Radu Chen, Bin Zhou, Yuanbo Wang, Hongwei Gao, Qinquan Tong, Tong Qian, Yanxin You, Lizhao Cong, Jingru Xiong, Lei Zhu, Shuyuan Zhong, Zhi-Qiang Lv, Kan Yang, Yang Tang, Kailing Zhang, Minjian Lei, Zhipei Xu, Zhe Zhang, Liwen Gou, Dingyong Wu, Yanlin Li, Cong Cui, Xiaohui Liu, Jiajia Xu, Guoyi Jiang, Yaoxin Shi, Yaokun Tu, Jiachen Wang, Liqing Li, Shihang Zhang, Bo Wang, Biao Xu, Haiming Long, Xiang Liao, Xurui Zhai, Yanqiao Li, Haozhe Shi, Shijun Zhang, Jiangning Liu, Yong Hu, Kai Xu, Jing Zeng, Xianfang Liu, Yuyang Wei, Minchen
author_facet	Guan, Ya-nan Zhang, Shaonan Guo, Hang Wang, Yawen Fan, Xinying Zhuang, Tianqu Liang, Jie Zeng, Hui Qin, Guanyi Qu, Lishen Dai, Tao Xia, Shu-Tao Zhang, Lei Timofte, Radu Chen, Bin Zhou, Yuanbo Wang, Hongwei Gao, Qinquan Tong, Tong Qian, Yanxin You, Lizhao Cong, Jingru Xiong, Lei Zhu, Shuyuan Zhong, Zhi-Qiang Lv, Kan Yang, Yang Tang, Kailing Zhang, Minjian Lei, Zhipei Xu, Zhe Zhang, Liwen Gou, Dingyong Wu, Yanlin Li, Cong Cui, Xiaohui Liu, Jiajia Xu, Guoyi Jiang, Yaoxin Shi, Yaokun Tu, Jiachen Wang, Liqing Li, Shihang Zhang, Bo Wang, Biao Xu, Haiming Long, Xiang Liao, Xurui Zhai, Yanqiao Li, Haozhe Shi, Shijun Zhang, Jiangning Liu, Yong Hu, Kai Xu, Jing Zeng, Xianfang Liu, Yuyang Wei, Minchen
contents	In this paper, we present a comprehensive overview of the NTIRE 2026 3rd Restore Any Image Model (RAIM) challenge, with a specific focus on Track 3: AI Flash Portrait. Despite significant advancements in deep learning for image restoration, existing models still encounter substantial challenges in real-world low-light portrait scenarios. Specifically, they struggle to achieve an optimal balance among noise suppression, detail preservation, and faithful illumination and color reproduction. To bridge this gap, this challenge aims to establish a novel benchmark for real-world low-light portrait restoration. We comprehensively evaluate the proposed algorithms utilizing a hybrid evaluation system that integrates objective quantitative metrics with rigorous subjective assessment protocols. For this competition, we provide a dataset containing 800 groups of real-captured low-light portrait data. Each group consists of a 1K-resolution low-light input image, a 1K ground truth (GT), and a 1K person mask. This challenge has garnered widespread attention from both academia and industry, attracting over 100 participating teams and receiving more than 3,000 valid submissions. This report details the motivation behind the challenge, the dataset construction process, the evaluation metrics, and the various phases of the competition. The released dataset and baseline code for this track are publicly available from the same \href{https://github.com/zsn1434/AI_Flash-BaseLine/tree/main}{GitHub repository}, and the official challenge webpage is hosted on \href{https://www.codabench.org/competitions/12885/}{CodaBench}.
format	Preprint
id	arxiv_https___arxiv_org_abs_2604_11230
institution	arXiv
publishDate	2026
record_format	arxiv
spellingShingle	NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3) Guan, Ya-nan Zhang, Shaonan Guo, Hang Wang, Yawen Fan, Xinying Zhuang, Tianqu Liang, Jie Zeng, Hui Qin, Guanyi Qu, Lishen Dai, Tao Xia, Shu-Tao Zhang, Lei Timofte, Radu Chen, Bin Zhou, Yuanbo Wang, Hongwei Gao, Qinquan Tong, Tong Qian, Yanxin You, Lizhao Cong, Jingru Xiong, Lei Zhu, Shuyuan Zhong, Zhi-Qiang Lv, Kan Yang, Yang Tang, Kailing Zhang, Minjian Lei, Zhipei Xu, Zhe Zhang, Liwen Gou, Dingyong Wu, Yanlin Li, Cong Cui, Xiaohui Liu, Jiajia Xu, Guoyi Jiang, Yaoxin Shi, Yaokun Tu, Jiachen Wang, Liqing Li, Shihang Zhang, Bo Wang, Biao Xu, Haiming Long, Xiang Liao, Xurui Zhai, Yanqiao Li, Haozhe Shi, Shijun Zhang, Jiangning Liu, Yong Hu, Kai Xu, Jing Zeng, Xianfang Liu, Yuyang Wei, Minchen Computer Vision and Pattern Recognition In this paper, we present a comprehensive overview of the NTIRE 2026 3rd Restore Any Image Model (RAIM) challenge, with a specific focus on Track 3: AI Flash Portrait. Despite significant advancements in deep learning for image restoration, existing models still encounter substantial challenges in real-world low-light portrait scenarios. Specifically, they struggle to achieve an optimal balance among noise suppression, detail preservation, and faithful illumination and color reproduction. To bridge this gap, this challenge aims to establish a novel benchmark for real-world low-light portrait restoration. We comprehensively evaluate the proposed algorithms utilizing a hybrid evaluation system that integrates objective quantitative metrics with rigorous subjective assessment protocols. For this competition, we provide a dataset containing 800 groups of real-captured low-light portrait data. Each group consists of a 1K-resolution low-light input image, a 1K ground truth (GT), and a 1K person mask. This challenge has garnered widespread attention from both academia and industry, attracting over 100 participating teams and receiving more than 3,000 valid submissions. This report details the motivation behind the challenge, the dataset construction process, the evaluation metrics, and the various phases of the competition. The released dataset and baseline code for this track are publicly available from the same \href{https://github.com/zsn1434/AI_Flash-BaseLine/tree/main}{GitHub repository}, and the official challenge webpage is hosted on \href{https://www.codabench.org/competitions/12885/}{CodaBench}.
title	NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)
topic	Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2604.11230