VQualA 2025 document image quality assessment challenge

Huang, Fan, Min, Xiongkuo, Ma, Zhichao, Liu, Xiaohong, Zhou, Chris Wei, Zhai, Guangtao, Gao, Junjie, Liu, Runze, Peng, Yingzhe, Yang, Shujian, Zhang, Jin, Yang, Kai, You, Zhiyuan, Ao, Michael, Wu, Yicheng, Zhang, Weixia, Chen, Junlin, Sun, Wei, Wang, Zhihua, Zhang, Zhe, Yang, Yang, Bai, Mingying, Du, Jiawang, Lu, Zilong, Jiang, Zhenyu, Cui, Ziguan, Gan, Zongliang, Tang, Guijin, Yang, Fan, Ouyang, Hang, Shi, Zhuohang, Xiao, Tianxin, Luo, Zhizun, Wu, Zhaowang, Deng, Kaixin, Zhang, Ruikun, Yang, Hao and Pan, Liyuan 2025. VQualA 2025 document image quality assessment challenge. Presented at: 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Honolulu, HI, USA, 19-20 October 2025. 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). IEEE, pp. 3344-3353. 10.1109/ICCVW69036.2025.00351

Full text not available from this repository.

Abstract

This paper reports on the VQualA 2025 Document Image Quality Assessment Challenge, which will be held in conjunction with the Visual Quality Assessment Competition Workshop (VQualA) at ICCV 2025. This challenge is to address a major challenge in the field of image processing, namely, image quality assessment (IQA) for enhanced document images. The challenge uses the IQA Dataset for enhanced document images (DIQA-5000), which has a total of 5000 enhanced document images with human-annotated Mean Opinion Scores (MOS), including diverse combinations of document enhancement algorithms. The challenge has a total of 120 registered participants. 16 participating teams submitted their prediction results during the development phase, with a total of 183 submissions. A total of 97 submissions were submitted by 16 participating teams during the final testing phase. Finally, 7 participating teams submitted their models and fact sheets, and detailed the methods they used. Some methods have achieved better results than baseline methods, and the winning methods have demonstrated superior prediction performance.

Item Type:	Conference or Workshop Item - published (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	IEEE
ISBN:	979-8-3315-8989-9
ISSN:	2473-9936
Last Modified:	20 Apr 2026 13:32
URI:	https://orca.cardiff.ac.uk/id/eprint/186502

Actions (repository staff only)

Edit Item