-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2025_CVPR, author = {Li, Xin and Yuan, Kun and Li, Bingchen and Guan, Fengbin and Shao, Yizhen and Yu, Zihao and Wang, Xijun and Lu, Yiting and Luo, Wei and Yao, Suhang and Sun, Ming and Zhou, Chao and Chen, Zhibo and Timofte, Radu and Zhang, Yabin and Zhang, Ao-Xiang and Zhi, Tianwu and Liu, Jianzhao and Li, Yang and Xu, Jingwen and Liao, Yiting and Zuo, Yushen and Wu, Mingyang and Li, Renjie and Zhong, Shengyun and Tu, Zhengzhong and Liu, Yufan and Chen, Xiangguang and Cao, Zuowei and Tang, Minhao and Liu, Shan and Zhang, Kexin and Xie, Jingfen and Wang, Yan and Chen, Kai and Zhao, Shijie and Zhang, Yunchen and Xu, Xiangkai and Gao, Hong and Shi, Ji and Bao, Yiming and Dong, Xiugang and Zhou, Xiangsheng and Tu, Yaofeng and Liang, Ying and Wang, Yiwen and Chai, Xinning and Zhang, Yuxuan and Cheng, Zhengxue and Qin, Yingsheng and Yang, Yucai and Xie, Rong and Song, Li and Sun, Wei and Fu, Kang and Cao, Linhan and Zhu, Dandan and Zhang, Kaiwei and Zhu, Yucheng and Zhang, Zicheng and Hu, Menghan and Min, Xiongkuo and Zhai, Guangtao and Jin, Zhi and Wu, Jiawei and Wang, Wei and Zhang, Wenjian and Lan, Yuhai and Yi, Gaoxiong and Na, Hengyuan and Luo, Wang and Wu, Di and Bai, MingYin and Du, Jiawang and Lu, Zilong and Jiang, Zhenyu and Zeng, Hui and Cui, Ziguan and Gan, Zongliang and Tang, Guijin and Xie, Xinglin and Song, Kehuan and Lu, Xiaoqiang and Jiao, Licheng and Liu, Fang and Liu, Xu and Chen, Puhua and Nguyen, Ha Thu and De Moor, Katrien and Amirshahi, Seyed Ali and Larabi, Mohamed-Chaker and Tang, Qi and He, Linfeng and Gao, Zhiyong and Gao, Zixuan and Zhang, Guohua and Huang, Zhiye and Deng, Yi and Jiang, Qingmiao and Chen, Lu and Yang, Yi and Liao, Xi and Nadir, Nourine Mohammed and Jiang, Yuxuan and Zhu, Qiang and Teng, Siyue and Zhang, Fan and Zhu, Shuyuan and Zeng, Bing and Bull, David and Liu, Meiqin and Yao, Chao and Zhao, Yao}, title = {NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {1092-1103} }
NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results
Abstract
This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement. The challenge comprises two tracks: (i) Efficient Video Quality Assessment (KVQ), and (ii) Diffusion-based Image Super-Resolution (KwaiSR). Track 1 aims to advance the development of lightweight and efficient video quality assessment (VQA) models, with an emphasis on eliminating reliance on model ensembles, redundant weights, and other computationally expensive components in the previous IQA/VQA competitions. Track 2 introduces a new short-form UGC dataset tailored for single-image super-resolution, i.e., the KwaiSR dataset. It consists of 1,800 synthetically generated S-UGC image pairs and 1,900 real-world S-UGC images, which are split into training, validation, and test sets using a ratio of 8:1:1. The primary objective of the challenge is to drive research that benefits the user experience of short-form UGC platforms such as Kwai and TikTok. This challenge attracted 266 participants and received 18 valid final submissions with corresponding fact sheets, significantly contributing to the progress of short-form UGC VQA and image super-resolution. The project is publicly available at https://github.com/lixinustc/KVQE-Challenge-CVPR-NTIRE2025
Related Material