Cover Image

NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Xin, Gong, Jiachao, Wang, Xijun, Xiong, Shiyao, Li, Bingchen, Yao, Suhang, Zhou, Chao, Chen, Zhibo, Timofte, Radu, Chen, Yuxiang, Yin, Shibo, Zhong, Yilian, Fang, Yushun, Zhu, Xilei, Wang, Yahui, Lu, Chen, Zheng, Meisong, Chen, Xiaoxu, Yang, Jing, Hu, Zhaokun, Liu, Jiahui, Chen, Ying, Bai, Haoran, Deng, Sibin, Li, Shengxi, Xu, Mai, Chen, Junyang, Chen, Hao, Zhu, Xinzhe, Zhang, Fengkai, Sun, Long, Yang, Yixing, Zhang, Xindong, Dong, Jiangxin, Pan, Jinshan, Zhang, Jiyuan, Liu, Shuai, Huang, Yibin, Wang, Xiaotao, Lei, Lei, Liu, Zhirui, Chen, Shinan, Sun, Shang-Quan, Ren, Wenqi, Xu, Jingyi, Chen, Zihong, Zou, Zhuoya, Qiu, Xiuhao, Ma, Jingyu, Fu, Huiyuan, Liu, Kun, Ma, Huadong, Feng, Dehao, Ma, Zhijie, Zhang, Boqi, Shi, Jiawei, Kang, Hao, Yang, Yixin, Jin, Yeying, Cheng, Xu, Jiang, Yuxuan, Zeng, Chengxi, Peng, Tianhao, Zhang, Fan, Bull, David, Xing, Yanan, Tu, Jiachen, Xu, Guoyi, Jiang, Yaoxin, Liu, Jiajia, Shi, Yaokun, Zhou, Wei, Li, Linfeng, Song, Hang, Xu, Qi, Yuan, Kun, Shao, Yizhen, Ren, Yulin
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866911586688434176
author	Li, Xin Gong, Jiachao Wang, Xijun Xiong, Shiyao Li, Bingchen Yao, Suhang Zhou, Chao Chen, Zhibo Timofte, Radu Chen, Yuxiang Yin, Shibo Zhong, Yilian Fang, Yushun Zhu, Xilei Wang, Yahui Lu, Chen Zheng, Meisong Chen, Xiaoxu Yang, Jing Hu, Zhaokun Liu, Jiahui Chen, Ying Bai, Haoran Deng, Sibin Li, Shengxi Xu, Mai Chen, Junyang Chen, Hao Zhu, Xinzhe Zhang, Fengkai Sun, Long Yang, Yixing Zhang, Xindong Dong, Jiangxin Pan, Jinshan Zhang, Jiyuan Liu, Shuai Huang, Yibin Wang, Xiaotao Lei, Lei Liu, Zhirui Chen, Shinan Sun, Shang-Quan Ren, Wenqi Xu, Jingyi Chen, Zihong Zou, Zhuoya Qiu, Xiuhao Ma, Jingyu Fu, Huiyuan Liu, Kun Ma, Huadong Feng, Dehao Ma, Zhijie Zhang, Boqi Shi, Jiawei Kang, Hao Yang, Yixin Jin, Yeying Cheng, Xu Jiang, Yuxuan Zeng, Chengxi Peng, Tianhao Zhang, Fan Bull, David Xing, Yanan Tu, Jiachen Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Shi, Yaokun Zhou, Wei Li, Linfeng Song, Hang Xu, Qi Yuan, Kun Shao, Yizhen Ren, Yulin
author_facet	Li, Xin Gong, Jiachao Wang, Xijun Xiong, Shiyao Li, Bingchen Yao, Suhang Zhou, Chao Chen, Zhibo Timofte, Radu Chen, Yuxiang Yin, Shibo Zhong, Yilian Fang, Yushun Zhu, Xilei Wang, Yahui Lu, Chen Zheng, Meisong Chen, Xiaoxu Yang, Jing Hu, Zhaokun Liu, Jiahui Chen, Ying Bai, Haoran Deng, Sibin Li, Shengxi Xu, Mai Chen, Junyang Chen, Hao Zhu, Xinzhe Zhang, Fengkai Sun, Long Yang, Yixing Zhang, Xindong Dong, Jiangxin Pan, Jinshan Zhang, Jiyuan Liu, Shuai Huang, Yibin Wang, Xiaotao Lei, Lei Liu, Zhirui Chen, Shinan Sun, Shang-Quan Ren, Wenqi Xu, Jingyi Chen, Zihong Zou, Zhuoya Qiu, Xiuhao Ma, Jingyu Fu, Huiyuan Liu, Kun Ma, Huadong Feng, Dehao Ma, Zhijie Zhang, Boqi Shi, Jiawei Kang, Hao Yang, Yixin Jin, Yeying Cheng, Xu Jiang, Yuxuan Zeng, Chengxi Peng, Tianhao Zhang, Fan Bull, David Xing, Yanan Tu, Jiachen Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Shi, Yaokun Zhou, Wei Li, Linfeng Song, Hang Xu, Qi Yuan, Kun Shao, Yizhen Ren, Yulin
contents	This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-UGC) video restoration benchmark, termed KwaiVIR, which is contributed by USTC and Kuaishou Technology. It contains both synthetically distorted videos and real-world short-form UGC videos in the wild. For this edition, the released data include 200 synthetic training videos, 48 wild training videos, 11 validation videos, and 20 testing videos. The primary goal of this challenge is to establish a strong and practical benchmark for restoring short-form UGC videos under complex real-world degradations, especially in the emerging paradigm of generative-model-based S-UGC video restoration. This challenge has two tracks: (i) the primary track is a subjective track, where the evaluation is based on a user study; (ii) the second track is an objective track. These two tracks enable a comprehensive assessment of restoration quality. In total, 95 teams have registered for this competition. And 12 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the KwaiVIR benchmark, demonstrating encouraging progress in short-form UGC video restoration in the wild.
format	Preprint
id	arxiv_https___arxiv_org_abs_2604_10551
institution	arXiv
publishDate	2026
record_format	arxiv
spellingShingle	NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results Li, Xin Gong, Jiachao Wang, Xijun Xiong, Shiyao Li, Bingchen Yao, Suhang Zhou, Chao Chen, Zhibo Timofte, Radu Chen, Yuxiang Yin, Shibo Zhong, Yilian Fang, Yushun Zhu, Xilei Wang, Yahui Lu, Chen Zheng, Meisong Chen, Xiaoxu Yang, Jing Hu, Zhaokun Liu, Jiahui Chen, Ying Bai, Haoran Deng, Sibin Li, Shengxi Xu, Mai Chen, Junyang Chen, Hao Zhu, Xinzhe Zhang, Fengkai Sun, Long Yang, Yixing Zhang, Xindong Dong, Jiangxin Pan, Jinshan Zhang, Jiyuan Liu, Shuai Huang, Yibin Wang, Xiaotao Lei, Lei Liu, Zhirui Chen, Shinan Sun, Shang-Quan Ren, Wenqi Xu, Jingyi Chen, Zihong Zou, Zhuoya Qiu, Xiuhao Ma, Jingyu Fu, Huiyuan Liu, Kun Ma, Huadong Feng, Dehao Ma, Zhijie Zhang, Boqi Shi, Jiawei Kang, Hao Yang, Yixin Jin, Yeying Cheng, Xu Jiang, Yuxuan Zeng, Chengxi Peng, Tianhao Zhang, Fan Bull, David Xing, Yanan Tu, Jiachen Xu, Guoyi Jiang, Yaoxin Liu, Jiajia Shi, Yaokun Zhou, Wei Li, Linfeng Song, Hang Xu, Qi Yuan, Kun Shao, Yizhen Ren, Yulin Computer Vision and Pattern Recognition This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-UGC) video restoration benchmark, termed KwaiVIR, which is contributed by USTC and Kuaishou Technology. It contains both synthetically distorted videos and real-world short-form UGC videos in the wild. For this edition, the released data include 200 synthetic training videos, 48 wild training videos, 11 validation videos, and 20 testing videos. The primary goal of this challenge is to establish a strong and practical benchmark for restoring short-form UGC videos under complex real-world degradations, especially in the emerging paradigm of generative-model-based S-UGC video restoration. This challenge has two tracks: (i) the primary track is a subjective track, where the evaluation is based on a user study; (ii) the second track is an objective track. These two tracks enable a comprehensive assessment of restoration quality. In total, 95 teams have registered for this competition. And 12 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the KwaiVIR benchmark, demonstrating encouraging progress in short-form UGC video restoration in the wild.
title	NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results
topic	Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2604.10551