XUE Tianfan

*SHB = Ho Sin Hang Engineering Building, The Chinese University of Hong Kong

Research Interest
  • Learning-based computational photography
  • Smart camera system
  • Image and video processing
  • 3D reconstruction and analysis
Courses Taught

  • IERG4190 Multimedia Coding and Processing

XUE Tianfan 薛天帆教授

Vice Chancellor Assistant Professor
BEng (THU), MPhil (CUHK), PhD (MIT)
(852) 3943-5255
Room 717, SHB*
tfxue [@] ie.cuhk.edu.hk
Website

Tianfan Xue received his Ph.D. from MIT Computer Science and Artificial Intelligence Laboratory, under the supervision of William T. Freeman. Before that, Tianfan Xue received his Master of Philosophy degree from the Information Engineering Department of the Chinese University of Hong Kong in 2011, and his B.E. degree from the Computer Science and Technology Department of Tsinghua University in 2009. He was a Staff Software Engineering in Google Research from 2017 to 2022. He was also a research intern at Facebook Research, Microsoft Research Redmond, Microsoft Research Cambridge, respectively in 2016, 2015, and 2014. He received outstanding reviewer awards at CVPR 2018. He also served as web chair of CVPR 2020, area chairs of WACV 2022 and CVPR 2023.

His research covers computational photography, machine learning, computer vision, and computer graphics. Particularly, he is interested in building a smart camera system and interact with visual world. These techniques benefit multiple areas, including AI-power vision system, mobile phone camera, self-driving, and medical imaging.

Recent / Selected Publications
  • Y. Jiang, B. Wronski, B. Mildenhall, J. T. Barron, Z. Wang, T. Xue, “Fast and High-Quality Image Denoising via Malleable Convolutions,” in Proc. of European Conference on Computer
    Vision (ECCV) 2022.
  • T. Xue, Chen, B., Wu, J., Wei, D. and Freeman, W.T., “Video enhancement with task-oriented flow,” International Journal of Computer Vision (IJCV), 8, pp.1106-1125, 2019.
  • T. Xue, J. Wu, K.L. Bouman, W.T. Freeman, “Visual dynamics: Stochastic future generation via layered cross convolutional networks,” IEEE transactions on pattern analysis and machine intelligence (T-PAMI), 41(9), pp.2236-2250, 2018.
  • J. Wu*, T. Xue*, J. Lim, Y. Tian, J. Tenenbaum, A. Torralba, W. T. Freeman, “3D Interpreter Networks for Viewer-Centered Wireframe Modeling,” International Journal of Computer Vi- sion (IJCV), pp.1009-1026, 2018.
  • T. Xue, M. Rubinstein, C. Liu, W. T. Freeman, “A Computational Approach for Obstruction-Free Photography,” ACM SIGGRAPH, 2015. – T. Xue, M. Rubinstein, N. Wadhwa, A. Levin, F. Durand, W. T. Freeman, “Refraction Wiggles for Measuring Fluid Depth and Velocity from Video,” in Proc. of European Conference on Computer Vision (ECCV), 2014.
Research Interest

  • Learning-based computational photography
  • Smart camera system
  • Image and video processing
  • 3D reconstruction and analysis
Courses Taught

  • IERG4190 Multimedia Coding and Processing