I am a Ph.D. student (2023) at the School of Artificial Intelligence, Xidian University, supervised by Prof. Leida Li. Prior to this, I received the B.Sc. degree from China University of Mining and Technology. My research interests include visual quality assessment and computational aesthetics. I serve as a reviewer for journals and conferences including TIP, PR, CVPR, AAAI, ACM MM, ECCV, etc.

🔥 News

2026.07: 🎉 Our paper AGIDefect-4K was accepted by ACM Multimedia 2026.
2026.04: 🎉 Awarded the 2026 Spring Outstanding Doctoral Dissertation Funding of Xidian University.
2026.01: 🎉 One paper accepted by ICASSP 2026.
2025.12: 🎉 Awarded the 2025 National Natural Science Foundation of China (NSFC) Youth Student Basic Research Grant.
2025.12: 🏆 Awarded the Huawei Scholarship of Xidian University.
2025.10: 🏆 Awarded the National Scholarship for Doctoral Students.
2025.11: 🎉 Two papers accepted by AAAI 2026.
2025.07: 🎉 One paper accepted by ACM Multimedia 2025.
2025.05: 🎉 One paper accepted by IEEE Transactions on Multimedia.
2025.03: 🎉 One paper accepted by ICME 2025.

📝 Publications

2026

ACM MM 2026

AGIDefect-4K: A Richly Annotated Dataset for AI-Generated Image Defect Detection, Localization and Explanation

Xiangfei Sheng, Weidong Zou, Tianjiao Gu, Zhichao Yang, Pengfei Chen, Leida Li

[Code]

AAAI 2026

Fine-grained Image Quality Assessment for Perceptual Image Restoration

Xiangfei Sheng, Xiaofeng Pan, Zhichao Yang, Pengfei Chen, Leida Li

[Paper] [Project] [Code]

AAAI 2026

TuningIQA: Fine-Grained Blind Image Quality Assessment for Livestreaming Camera Tuning

Xiangfei Sheng, Zhichao Duan, Xiaofeng Pan, Yipo Huang, Zhichao Yang, Pengfei Chen, Leida Li

[Paper]

2025

ACM MM 2025

InstructCrop: Teaching Multimodal Large Language Models to Crop Aesthetic Images

Xiangfei Sheng, Pangu Xie, Weidong Zou, Pengfei Chen, Tong Zhu, Leida Li

[Paper] [Code]

ICME 2025

Text-to-Image Diffusion Models are AI-Generated Image Quality Scorers

Xiangfei Sheng, Weidong Zou, Pengfei Chen, Li Cai, Chao He, Leida Li

[Paper] [Code]

IEEE TMM 2025

AesPrompt: Zero-Shot Image Aesthetics Assessment With Multi-Granularity Aesthetic Prompt Learning

Xiangfei Sheng, Leida Li, Pengfei Chen, Li Cai, Giuseppe Valenzise

[Paper] [Code]

2024

ACM MM 2024

AesExpert: Towards Multi-Modality Foundation Model for Image Aesthetics Perception

Yipo Huang, Xiangfei Sheng, Zhichao Yang, Quan Yuan, Zhichao Duan, Pengfei Chen, Leida Li, Weisi Lin, Guangming Shi

[Paper] [Project] [Code]

arXiv 2024

AesBench: Benchmarking Multimodal Large Language Models on Image Aesthetics Understanding

Yipo Huang, Quan Yuan, Xiangfei Sheng, Zhichao Yang, Haoning Wu, Pengfei Chen, Yuzhe Yang, Leida Li, Weisi Lin

[Paper] [Code]

IEEE TCSVT 2024

Towards Explainable Image Aesthetics Assessment with Attribute-Oriented Critiques Generation

Leida Li, Xiangfei Sheng, Pengfei Chen, Jinjian Wu, Weisheng Dong

[Paper] [Code]

2023

ACM MM 2023

AesCLIP: Multi-Attribute Contrastive Learning for Image Aesthetics Assessment

Xiangfei Sheng, Leida Li, Pengfei Chen, Jinjian Wu, Weisheng Dong, Yuzhe Yang, Liwu Xu, Yaqian Li, Guangming Shi

[Paper] [Code]

🎖 Honors and Awards

2025.10 National Scholarship for Doctoral Students, Xidian University.
2025.12 Huawei Scholarship, Xidian University.
2024.06 🏆 Winner Award, CVPR NTIRE 2024 DXOMARK Portrait Quality Assessment Challenge.

💻 Internships

2022.10 - 2023.05, Research Intern, OPPO Research Institute, Shanghai, China.