Welcome to MediaX@SJTU (上交智能媒体组)

MediaX is a research group under the Cooperative Medianet Innovation Center at Shanghai Jiao Tong University, focusing on cutting-edge research at the intersection of computer vision, machine learning, and generative intelligent media. We aim to advance the frontiers of multi-modal media (2D/3D/4D) across generation, restoration and enhancement, reconstruction and compression, and quality assessment. Our mission is to build intelligent systems capable of understanding, modeling, and manipulating complex human-centric visual content, enabling the high-quality and efficient creation of next-generation intelligent media.

🎯 Research Focus

Media Perception & Quality Assessment
Developing intelligent, multi-dimensional evaluation systems for UGC, PGC, and AIGC content.

Video Restoration & Generation
Enhancing, controllably generating and editing 4K/8K video content.

3D/4D Reconstruction & Generation
Leveraging 3DGS and GenAI for efficient representation and compression of immersive dynamic scenes.

Intelligent Media Creation Platform
Building collaborative, multi-agent systems for automated and interactive media production.

📢 Join Us

We are always looking for self-motivated PhD students, Master's students, and undergraduate RA to join our team.
If you're passionate about intelligent media and generative AI, please send your CV and transcript to: mediax@sjtu.edu.cn

[ICCV'2025] F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration Lu Liu, Huiyu Duan, Qiang Hu, Liu Yang, Chunlei Cai, Tianxiao Ye, Huayu Liu, Xiaoyun Zhang, Guangtao Zhai IEEE/CVF International Conference on Computer Vision (ICCV), 2025. [Paper]

[ICME'2025] Serial Low-rank Adaptation of Vision Transformer Houqiang Zhong, Shaocheng Shen, Ke Cai, Zhenglong Wu, Jiangchao Yao, Yuan Cheng, Xuefei Li, Xiaoyun Zhang, Li Song, Qiang Hu IEEE International Conference on Multimedia and Expo (ICME), 2025. [Paper]

[ICME'2025]TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restoration Ziying Zhang, Xiang Gao, Zhixin Wang, Qiang Hu, Xiaoyun Zhang IEEE International Conference on Multimedia and Expo (ICME), 2025. [Paper]

[CVPR'2025]4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video Qiang Hu, Zihan Zheng, Houqiang Zhong, Sihua Fu, Li Song, Xiaoyun Zhang, Guangtao Zhai, Yanfeng Wang. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. [Paper] [Code]

[AAAI'2025] VRVVC: Variable-Rate NeRF-Based Volumetric Video Compression Qiang Hu,Houqiang Zhong,Zihan Zheng,Xiaoyun Zhang,Zhengxue Cheng,Li Song,Guangtao Zhai,Yanfeng Wang The Association for the Advancement of Artificial Intelligence (AAAI), 2025. [Paper]

[WACV'2025] MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning Haoning Wu, Shaocheng Shen, Qiang Hu, Xiaoyun Zhang, Ya Zhang, Yanfeng Wang Winter Conference on Applications of Computer Vision (WACV), 2025. [Paper]

More on publication page