-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2025_CVPR, author = {Liu, Xiaohong and Min, Xiongkuo and Hu, Qiang and Zhang, Xiaoyun and Guo, Jie and Zhai, Guangtao and Wang, Shushi and Zhou, Yingjie and Liu, Lu and Li, Jingxin and Yang, Liu and Wen, Farong and Xu, Li and Jiang, Yanwei and Zhu, Xilei and Li, Chunyi and Zhang, Zicheng and Duan, Huiyu and Wu, Xiele and Gao, Yixuan and Cao, Yuqin and Jia, Jun and Sun, Wei and Cao, Jiezhang and Timofte, Radu and Li, Baojun and Huang, Jiamian and Luo, Dan and Liu, Tao and Zhang, Weixia and Zheng, Bingkun and Chen, Junlin and Zhou, Ruikai and Chen, Meiya and Wang, Yu and Jiang, Hao and Li, Xiantao and Jiang, Yuxiang and Tang, Jun and Zhao, Yimeng and Hu, Bo and Qi, Zelu and Zhang, Chaoyang and Zhao, Fei and Shi, Ping and Fu, Lingzhi and Cong, Heng and He, Shuai and Zhang, Rongyu and He, Jiarong and Hu, Zongyao and Luo, Wei and Yu, Zihao and Guan, Fengbin and Lu, Yiting and Li, Xin and Chen, Zhibo and Su, Mengjing and Wang, Yi and Chen, Tuo and Li, Chunxiao and Zhao, Shuaiyu and Wen, Jiaxin and Lin, Chuyi and Liu, Sitong and Chu, Ningxin and Wan, Jing and Zhou, Yu and Chen, Baoying and Zeng, Jishen and Liu, Jiarui and Liu, Xianjin and Chen, Xin and Zhou, Lanzhi and Li, Hangyu and Han, You and Xiang, Bibo and Liu, Zhenjie and Lu, Jianzhang and Gui, Jialin and Lu, Renjie and Wang, Shangfei and Zhou, Donghao and Lin, Jingyu and Song, Quanjian and Huang, Jiancheng and Yang, Yufeng and Wang, Changwei and Zhong, Shupeng and Yang, Yang and He, Lihuo and Liu, Jia and Xing, Yuting and Fang, Tida and Jin, Yuchun}, title = {NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2025}, pages = {1389-1402} }
NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results
Abstract
This paper reports on the NTIRE 2025 XGC Quality Assessment Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. This challenge is to address a major challenge in the field of video and talking head processing. The challenge is divided into three tracks, including user generated video, AI generated video and talking head. The user-generated video track uses the FineVD-GC, which contains 6,284 user generated videos. The user-generated video track has a total of 125 registered participants. A total of 242 submissions are received in the development phase, and 136 submissions are received in the test phase. Finally, 5 participating teams submitted their models and fact sheets. The AI generated video track uses the Q-Eval-Video, which contains 34,029 AI-Generated Videos (AIGVs) generated by 11 popular Text-to-Video (T2V) models. A total of 133 participants have registered in this track. A total of 396 submissions are received in the development phase, and 226 submissions are received in the test phase. Finally, 6 participating teams submitted their models and fact sheets. The talking head track uses the THQA-NTIRE, which contains 12,247 2D and 3D talking heads. A total of 89 participants have registered in this track. A total of 225 submissions are received in the development phase, and 118 submissions are received in the test phase. Finally, 8 participating teams submitted their models and fact sheets. Each participating team in every track has proposed a method that outperforms the baseline, which has contributed to the development of fields in three tracks.
Related Material