Xiaohang (Joshua) Yang

PhD Student
Yuan Lab, Digital Environment Research Institute, Queen Mary University of London, London
Office: Ground Floor, DERI, Empire House

Hi there! This is Xiaohang. I am currently a PhD student at Yuan Lab, Digital Environment Research Institute (DERI), supervised by Dr. Shanxin Yuan and Prof. Dr. Greg Slabaugh. My research interests lie in digital human, neural rendering and video perception. In particular, I study motion retargeting, motion generation and neural rendering of dynmaic human bodies at present.

Previously, I got my Master's and Bachelor's degree in Control Science and Engineering (Computer Vision and Pattern Recognition Direction) at Shanghai Jiao Tong University (SJTU). During my postgraduate, I joined the Institute of Image Processing and Pattern Recognition and worked with Prof. Dr. Jie Yang. After this, I joined 3DNR Group, Autonomous Driving Group, Shanghai AI Lab as an intern researcher.

News

Sep 20, 2023 Joined DERI, QMUL, as a PhD student.
Sep 30, 2022 Homepage rebuilt. :sparkles:

Education

Sept 2023 - present Ph.D. in Computer Games and Animation, Queen Mary University of London (QMUL)
Sept 2019 - May 2022 M.S. in Control Science and Engineering, Shanghai Jiao Tong University (SJTU)
Sept 2015 - Jun 2019 B.S. in Automation, Shanghai Jiao Tong University (SJTU)

Work Experience

Nov 2021 - Mar 2023 Research Intern, 3D Neural Rendering Group, Autonomous Driving Group, Shanghai AI Lab.
Sept 2019 - Jun 2022 Research Assistant, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University (SJTU), supervised by Prof. Dr. Jie Yang.

Publications

  1. ECCVW
    Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss
    Qifan Fu, Xiaohang Yang, Muhammad Asad, Changjae Oh, Shanxin Yuan, and Gregory Slabaugh
    European Conference on Computer Vision, HANDS Workshop (ECCV HANDS Workshop) , 2024
    PDF
  2. Graduate Thesis
    Efficient Frame Interpolation Algorithm
    Xiaohang Yang
    Master Degree Thesis (Graduate Thesis) , 2022
  3. ICASSP
    Unsupervised Motion Representation Enhanced Network for Action Recognition
    Xiaohang Yang, Lingtong Kong, and Jie Yang
    International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2021
    PDF
  4. ICASSP
    Oas-net: Occlusion aware sampling network for accurate optical flow
    Lingtong Kong, Xiaohang Yang, and Jie Yang
    International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2021
    PDF
  5. arXiv
    Homography Estimation Network Based on Dense Correspondence
    Xiaohang Yang, Lingtong Kong, Ziyun Liang, and Jie Yang
    arXiv pre-print (arXiv) , 2021
    PDF

Projects

Categorical and Deformable Neural Representation

Pedestrian Reconstruction.
Vehicle Reconstruction.

Neural Rendering of Dynamic Scenes

Reproduce the Scene with Fixed Time.
Reproduce the Scene with Fixed Viewpoint.

Video Frame Interpolation

Original Video Frames.
8x Interpolation & Smoother Motion.

Optical Flow & Action Recognition

Optical Flow Estimation on KITTI.
Action Recognition Enhanced by Unsupervised Optical Flow.
Please refer to the Projects Page for more details.