UP Lab


Xiatian Zhu, a Senior Lecturer affiliated with the Surrey Institute for People-Centred Artificial Intelligence and the Centre for Vision, Speech and Signal Processing (CVSSP) at the University of Surrey in Guildford, UK, leads the Universal Perception (UP) Lab. Previously a research scientist at Samsung AI Centre, Cambridge, UK, Dr. Zhu holds a Ph.D. from the Queen Mary University of London.

The UP Lab is dedicated to advancing AI capabilities by modelling diverse perception data, such as images, videos, audio, text, 3D points, LiDAR, and remote sensing. Application domains span computer vision, healthcare, weather and climate, finance, cybersecurity, and social issues. Our work emphasizes the intersection of machine learning theories and real-world domain applications, aiming to develop transformative technologies for societal benefit.

For inquiries about research collaboration and student opportunities, please contact us.


Jun 4, 2024 Welcome Zhe Zhang visiting the UP lab
May 6, 2024 Welcome Yuchao Li visiting the UP lab
Mar 11, 2024 Welcome Tian Zhang visiting the UP lab
Mar 8, 2024 1 CVPR paper accepted
Jan 16, 2024 1 ICLR paper on high-resolution 3D object generation accepted

Selected publications

  1. ICLR
    Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping
    Pan, Zijie, Lu, Jiachen,  Zhu, Xiatian, and Zhang, Li
    In International Conference on Learning Representations 2024
  2. CVPR
    Source-Free Domain Adaptation with Frozen Multimodal Foundation Model
    Tang, Song, Su, Wenxin, Ye, Mao, and Zhu, Xiatian
    In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2024
  3. AAAI (oral)
    DiffSED: Sound Event Detection with Denoising Diffusion
    Bhosale, Swapnil, Nag, Sauradip, Kanojia, Diptesh, Deng, Jiankang, and Zhu, Xiatian
    In AAAI Conference on Artificial Intelligence 2024
  4. TPAMI
    Compressed-SDR to HDR Video Reconstruction
    Wang, Hu, Ye, Mao,  Zhu, Xiatian, Li, Shuai, Li, Xue, and Zhu, Ce
    IEEE Transactions on Pattern Analysis and Machine Intelligence 2024