Visual Quality Assessment Competition
VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2025_ICCV, author = {Zhu, Hanwei and Wu, Haoning and Zhang, Zicheng and Zhu, Lingyu and Li, Yixuan and Chen, Peilin and Wang, Shiqi and Zhou, Chris Wei and Cao, Linhan and Sun, Wei and Zhu, Xiangyang and Zhang, Weixia and Zhu, Yucheng and Liu, Jing and Zhu, Dandan and Zhai, Guangtao and Min, Xiongkuo and Zhang, Zhichao and Li, Xinyue and Xu, Shubo and Dao, Anh and Li, Yifan and Yu, Hongyuan and Yi, Jiaojiao and Tian, Yiding and Wu, Yupeng and Sun, Feiran and Jiao, Lijuan and Jiang, Song}, title = {VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3352-3362} }
VQualA 2025 Document Image Quality Assessment Challenge-
[pdf]
[bibtex]@InProceedings{Huang_2025_ICCV, author = {Huang, Fan and Min, Xiongkuo and Ma, Zhichao and Liu, Xiaohong and Zhou, Chris Wei and Zhai, Guangtao and Gao, Junjie and Liu, Runze and Peng, Yingzhe and Yang, Shujian and Zhang, Jin and Yang, Kai and You, Zhiyuan and Ao, Zitian and Wu, Yicheng and Zhang, Weixia and Chen, Junlin and Sun, Wei and Wang, Zhihua and Zhang, Zhe and Yang, Yang and Bai, Mingying and Du, Jiawang and Lu, Zilong and Jiang, Zhenyu and Cui, Ziguan and Gan, Zongliang and Tang, Guijin and Yang, Fan and Ouyang, Hang and Shi, Zhuohang and Xiao, Tianxin and Luo, Zhizun and Wu, Zhaowang and Deng, Kaixin and Zhang, Ruikun and Yang, Hao and Pan, Liyuan}, title = {VQualA 2025 Document Image Quality Assessment Challenge}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3313-3322} }
VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2025_ICCV, author = {Li, Dasong and Ma, Sizhuo and Hua, Hang and Li, Wenjie and Wang, Jian and Zhou, Chris Wei and Guan, Fengbin and Li, Xin and Yu, Zihao and Lu, Yiting and Liao, Ru-Ling and Ye, Yan and Chen, Zhibo and Sun, Wei and Cao, Linhan and Cao, Yuqin and Zhang, Weixia and Wen, Wen and Zhang, Kaiwei and Chen, Zijian and Lu, Fangfang and Min, Xiongkuo and Zhai, Guangtao and Xiao, Erjia and Zhang, Lingfeng and Su, Zhenjie and Cheng, Hao and Liu, Yu and Xu, Renjing and Chen, Long and Hao, Xiaoshuai and Zeng, Zhenpeng and Wu, Jianqin and Wang, Xuxu and Yu, Qian and Hu, Bo and Wang, Weiwei and Liu, Pinxin and Tang, Yunlong and Song, Luchuan and He, Jinxi and Wu, Jiarui and Lyu, Hanjia}, title = {VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3391-3401} }
PKU-AIGIQA-4K: A Perceptual Quality Assessment Database for Both Text-to-Image and Image-to-Image AI-Generated Images-
[pdf]
[supp]
[bibtex]@InProceedings{Yuan_2025_ICCV, author = {Yuan, Jiquan and Li, Jihe and Yang, Fanyi and Cao, Xinyan and Che, Jinming and Lin, Jinlong and Cao, Xixin}, title = {PKU-AIGIQA-4K: A Perceptual Quality Assessment Database for Both Text-to-Image and Image-to-Image AI-Generated Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3331-3340} }
VQualA 2025 Challenge on Image Super-Resolution Generated Content Quality Assessment: Methods and Results-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2025_ICCV, author = {Li, Yixiao and Li, Xin and Zhou, Chris Wei and Xing, Shuo and Amirpour, Hadi and Hao, Xiaoshuai and Yue, Guanghui and Zhao, Baoquan and Liu, Weide and Yang, Xiaoyuan and Tu, Zhengzhong and Li, Xinyu and Song, Chuanbiao and Zhang, Chenqi and Lan, Jun and Zhu, Huijia and Wang, Weiqiang and Sun, Xiaoyan and Tian, Shishun and Yan, Dongyang and Zhang, Weixia and Chen, Junlin and Sun, Wei and Wang, Zhihua and Shi, Zhuohang and Luo, Zhizun and Ouyang, Hang and Xiao, Tianxin and Yang, Fan and Wu, Zhaowang and Deng, Kaixin}, title = {VQualA 2025 Challenge on Image Super-Resolution Generated Content Quality Assessment: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3341-3351} }
DeQA-Doc: Adapting DeQA-Score to Document Image Quality Assessment-
[pdf]
[bibtex]@InProceedings{Gao_2025_ICCV, author = {Gao, Junjie and Liu, Runze and Peng, Yingzhe and Yang, Shujian and Zhang, Jin and Yang, Kai and You, Zhiyuan}, title = {DeQA-Doc: Adapting DeQA-Score to Document Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3428-3437} }
Hybrid Vision Transformer and Convolutional Neural Network for Super-Resolution Image Quality Assessment-
[pdf]
[bibtex]@InProceedings{Li_2025_ICCV, author = {Li, Xinyu and Song, Chuanbiao and Zhang, Chenqi and Lan, Jun and Zhu, Huijia and Wang, Weiqiang and Sun, Xiaoyan}, title = {Hybrid Vision Transformer and Convolutional Neural Network for Super-Resolution Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3323-3330} }
Better Supervised Fine-tuning for VQA: Integer-Only Loss-
[pdf]
[arXiv]
[bibtex]@InProceedings{Qian_2025_ICCV, author = {Qian, Baihong and Fan, Haotian and Liao, Wenjie and Wang, Yunqiu and Li, Tao and Cui, Junhui}, title = {Better Supervised Fine-tuning for VQA: Integer-Only Loss}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3303-3312} }
RankCORE: Self-Supervised Ranking-Aware Correlation Optimized Regression for Face Image Quality Assessment-
[pdf]
[bibtex]@InProceedings{Joshi_2025_ICCV, author = {Joshi, Abhishek and Agarwal, Aman}, title = {RankCORE: Self-Supervised Ranking-Aware Correlation Optimized Regression for Face Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3466-3474} }
AIGVQA: A Unified Framework for Multi-Dimensional Quality Assessment of AI-Generated Video-
[pdf]
[bibtex]@InProceedings{Wang_2025_ICCV, author = {Wang, Jiarui and Wang, Juntong and Zhu, Xiaorong and Duan, Huiyu and Zhai, Guangtao and Min, Xiongkuo}, title = {AIGVQA: A Unified Framework for Multi-Dimensional Quality Assessment of AI-Generated Video}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3383-3390} }
Exploring MLLM in Fine-Grained Visual Quality Comparison with Quality Token-
[pdf]
[bibtex]@InProceedings{Jiang_2025_ICCV, author = {Jiang, Song and Jiao, Lijuan and Li, Yuguang and You, Pei and Li, Hui and Yang, Ran and Zhu, Feng and Ki, Sehwan and Lee, Hyong-Euk}, title = {Exploring MLLM in Fine-Grained Visual Quality Comparison with Quality Token}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3475-3485} }
Engagement Prediction of Short Videos with Large Multimodal Models-
[pdf]
[arXiv]
[bibtex]@InProceedings{Sun_2025_ICCV, author = {Sun, Wei and Cao, Linhan and Cao, Yuqin and Zhang, Weixia and Wen, Wen and Zhang, Kaiwei and Chen, Zijian and Lu, Fangfang and Min, Xiongkuo and Zhai, Guangtao}, title = {Engagement Prediction of Short Videos with Large Multimodal Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3402-3411} }
Efficient Face Image Quality Assessment via Self-training and Knowledge Distillation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Sun_2025_ICCV, author = {Sun, Wei and Zhang, Weixia and Cao, Linhan and Jia, Jun and Zhu, Xiangyang and Zhu, Dandan and Min, Xiongkuo and Zhai, Guangtao}, title = {Efficient Face Image Quality Assessment via Self-training and Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3363-3371} }
QualiVision: Multi-Modal Video Quality Assessment with Quality-Aware Fusion and Discriminative Learning Strategies-
[pdf]
[bibtex]@InProceedings{Bompilwar_2025_ICCV, author = {Bompilwar, Ritik and Koshatwar, Saurabh}, title = {QualiVision: Multi-Modal Video Quality Assessment with Quality-Aware Fusion and Discriminative Learning Strategies}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3438-3447} }
Perceptual Classifiers: Detecting Generative Images using Perceptual Features-
[pdf]
[arXiv]
[bibtex]@InProceedings{Durbha_2025_ICCV, author = {Durbha, Krishna Srikar and Venkataramanan, Asvin Kumar and Sureddi, Rajesh and Bovik, Alan}, title = {Perceptual Classifiers: Detecting Generative Images using Perceptual Features}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3372-3382} }
MMF-QE: Advanced Multi-Modal Fusion for Quality Assessment and Engagement Prediction in User-Generated Short Videos-
[pdf]
[bibtex]@InProceedings{Guan_2025_ICCV, author = {Guan, Fengbin and Yu, Zihao and Lu, Yiting and Luo, Wei and Gao, Yixin and Li, Xin and Chen, Zhibo}, title = {MMF-QE: Advanced Multi-Modal Fusion for Quality Assessment and Engagement Prediction in User-Generated Short Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3458-3465} }
A Lightweight Ensemble-Based Face Image Quality Assessment Method with Correlation-Aware Loss-
[pdf]
[arXiv]
[bibtex]@InProceedings{Hamidi_2025_ICCV, author = {Hamidi, Mohammadali and Amirpour, Hadi and Atzori, Luigi and Timmerer, Christian}, title = {A Lightweight Ensemble-Based Face Image Quality Assessment Method with Correlation-Aware Loss}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3420-3427} }
VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ma_2025_ICCV, author = {Ma, Sizhuo and Chen, Wei-Ting and Gao, Qiang and Wang, Jian and Zhou, Chris Wei and Sun, Wei and Zhang, Weixia and Cao, Linhan and Jia, Jun and Zhu, Xiangyang and Zhu, Dandan and Min, Xiongkuo and Zhai, Guangtao and Chen, Baoying and Xiao, Xiongwei and Zeng, Jishen and Wu, Wei and Lou, Tiexuan and Tan, Yuchen and Song, Chunyi and Xu, Zhiwei and Hamidi, MohammadAli and Amirpour, Hadi and Bai, Mingyin and Du, Jiawang and Jiang, Zhenyu and Lu, Zilong and Cui, Ziguan and Gan, Zongliang and Li, Xinpeng and Jiang, Shiqi and Li, Chenhui and Wang, Changbo and Yuan, Weijun and Li, Zhan and Chen, Yihang and Deng, Yifan and Deng, Ruting and Chen, Zhanglu and Yao, Boyang and Zheng, Shuling and Zhang, Feng and Fu, Zhiheng and Joshi, Abhishek and Agarwal, Aman and Immidisetti, Rakhil and Mopidevi, Ajay Narasimha and Shukla, Vishwajeet and Yang, Hao and Zhang, Ruikun and Pan, Liyuan and Deng, Kaixin and Ouyang, Hang and Yang, Fan and Luo, Zhizun and Shi, Zhuohang and Lai, Songning and Ruan, Weilin and Yue, Yutao}, title = {VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3448-3457} }
Understanding Perceptual Quality in CCTV Images: A Benchmark Dataset and Entropy-based Insights-
[pdf]
[bibtex]@InProceedings{Han_2025_ICCV, author = {Han, Yujin and Kang, Jiwoo and Lee, Sanghoon and Kim, Taewan}, title = {Understanding Perceptual Quality in CCTV Images: A Benchmark Dataset and Entropy-based Insights}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3412-3419} }