Buchumschlag

VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Ma, Sizhuo, Chen, Wei-Ting, Gao, Qiang, Wang, Jian, Zhou, Chris Wei, Sun, Wei, Zhang, Weixia, Cao, Linhan, Jia, Jun, Zhu, Xiangyang, Zhu, Dandan, Min, Xiongkuo, Zhai, Guangtao, Chen, Baoying, Xiao, Xiongwei, Zeng, Jishen, Wu, Wei, Lou, Tiexuan, Tan, Yuchen, Song, Chunyi, Xu, Zhiwei, Hamidi, MohammadAli, Amirpour, Hadi, Bai, Mingyin, Du, Jiawang, Jiang, Zhenyu, Lu, Zilong, Cui, Ziguan, Gan, Zongliang, Li, Xinpeng, Jiang, Shiqi, Li, Chenhui, Wang, Changbo, Yuan, Weijun, Li, Zhan, Chen, Yihang, Deng, Yifan, Deng, Ruting, Chen, Zhanglu, Yao, Boyang, Zheng, Shuling, Zhang, Feng, Fu, Zhiheng, Joshi, Abhishek, Agarwal, Aman, Immidisetti, Rakhil, Mopidevi, Ajay Narasimha, Shukla, Vishwajeet, Yang, Hao, Zhang, Ruikun, Pan, Liyuan, Deng, Kaixin, Ouyang, Hang, yang, Fan, Luo, Zhizun, Shi, Zhuohang, Lai, Songning, Ruan, Weilin, Yue, Yutao
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

_version_	1866914005404090368
author	Ma, Sizhuo Chen, Wei-Ting Gao, Qiang Wang, Jian Zhou, Chris Wei Sun, Wei Zhang, Weixia Cao, Linhan Jia, Jun Zhu, Xiangyang Zhu, Dandan Min, Xiongkuo Zhai, Guangtao Chen, Baoying Xiao, Xiongwei Zeng, Jishen Wu, Wei Lou, Tiexuan Tan, Yuchen Song, Chunyi Xu, Zhiwei Hamidi, MohammadAli Amirpour, Hadi Bai, Mingyin Du, Jiawang Jiang, Zhenyu Lu, Zilong Cui, Ziguan Gan, Zongliang Li, Xinpeng Jiang, Shiqi Li, Chenhui Wang, Changbo Yuan, Weijun Li, Zhan Chen, Yihang Deng, Yifan Deng, Ruting Chen, Zhanglu Yao, Boyang Zheng, Shuling Zhang, Feng Fu, Zhiheng Joshi, Abhishek Agarwal, Aman Immidisetti, Rakhil Mopidevi, Ajay Narasimha Shukla, Vishwajeet Yang, Hao Zhang, Ruikun Pan, Liyuan Deng, Kaixin Ouyang, Hang yang, Fan Luo, Zhizun Shi, Zhuohang Lai, Songning Ruan, Weilin Yue, Yutao
author_facet	Ma, Sizhuo Chen, Wei-Ting Gao, Qiang Wang, Jian Zhou, Chris Wei Sun, Wei Zhang, Weixia Cao, Linhan Jia, Jun Zhu, Xiangyang Zhu, Dandan Min, Xiongkuo Zhai, Guangtao Chen, Baoying Xiao, Xiongwei Zeng, Jishen Wu, Wei Lou, Tiexuan Tan, Yuchen Song, Chunyi Xu, Zhiwei Hamidi, MohammadAli Amirpour, Hadi Bai, Mingyin Du, Jiawang Jiang, Zhenyu Lu, Zilong Cui, Ziguan Gan, Zongliang Li, Xinpeng Jiang, Shiqi Li, Chenhui Wang, Changbo Yuan, Weijun Li, Zhan Chen, Yihang Deng, Yifan Deng, Ruting Chen, Zhanglu Yao, Boyang Zheng, Shuling Zhang, Feng Fu, Zhiheng Joshi, Abhishek Agarwal, Aman Immidisetti, Rakhil Mopidevi, Ajay Narasimha Shukla, Vishwajeet Yang, Hao Zhang, Ruikun Pan, Liyuan Deng, Kaixin Ouyang, Hang yang, Fan Luo, Zhizun Shi, Zhuohang Lai, Songning Ruan, Weilin Yue, Yutao
contents	Face images play a crucial role in numerous applications; however, real-world conditions frequently introduce degradations such as noise, blur, and compression artifacts, affecting overall image quality and hindering subsequent tasks. To address this challenge, we organized the VQualA 2025 Challenge on Face Image Quality Assessment (FIQA) as part of the ICCV 2025 Workshops. Participants created lightweight and efficient models (limited to 0.5 GFLOPs and 5 million parameters) for the prediction of Mean Opinion Scores (MOS) on face images with arbitrary resolutions and realistic degradations. Submissions underwent comprehensive evaluations through correlation metrics on a dataset of in-the-wild face images. This challenge attracted 127 participants, with 1519 final submissions. This report summarizes the methodologies and findings for advancing the development of practical FIQA approaches.
format	Preprint
id	arxiv_https___arxiv_org_abs_2508_18445
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results Ma, Sizhuo Chen, Wei-Ting Gao, Qiang Wang, Jian Zhou, Chris Wei Sun, Wei Zhang, Weixia Cao, Linhan Jia, Jun Zhu, Xiangyang Zhu, Dandan Min, Xiongkuo Zhai, Guangtao Chen, Baoying Xiao, Xiongwei Zeng, Jishen Wu, Wei Lou, Tiexuan Tan, Yuchen Song, Chunyi Xu, Zhiwei Hamidi, MohammadAli Amirpour, Hadi Bai, Mingyin Du, Jiawang Jiang, Zhenyu Lu, Zilong Cui, Ziguan Gan, Zongliang Li, Xinpeng Jiang, Shiqi Li, Chenhui Wang, Changbo Yuan, Weijun Li, Zhan Chen, Yihang Deng, Yifan Deng, Ruting Chen, Zhanglu Yao, Boyang Zheng, Shuling Zhang, Feng Fu, Zhiheng Joshi, Abhishek Agarwal, Aman Immidisetti, Rakhil Mopidevi, Ajay Narasimha Shukla, Vishwajeet Yang, Hao Zhang, Ruikun Pan, Liyuan Deng, Kaixin Ouyang, Hang yang, Fan Luo, Zhizun Shi, Zhuohang Lai, Songning Ruan, Weilin Yue, Yutao Computer Vision and Pattern Recognition Face images play a crucial role in numerous applications; however, real-world conditions frequently introduce degradations such as noise, blur, and compression artifacts, affecting overall image quality and hindering subsequent tasks. To address this challenge, we organized the VQualA 2025 Challenge on Face Image Quality Assessment (FIQA) as part of the ICCV 2025 Workshops. Participants created lightweight and efficient models (limited to 0.5 GFLOPs and 5 million parameters) for the prediction of Mean Opinion Scores (MOS) on face images with arbitrary resolutions and realistic degradations. Submissions underwent comprehensive evaluations through correlation metrics on a dataset of in-the-wild face images. This challenge attracted 127 participants, with 1519 final submissions. This report summarizes the methodologies and findings for advancing the development of practical FIQA approaches.
title	VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results
topic	Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2508.18445