About

I’m Tianhan Xu (徐 天涵), a first-year Ph.D student at Machine Intelligence Lab., supervised by Prof. Tatsuya Harada. I am also affiliated with Preferred Networks, Inc. as a researcher.

Publication

  • HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation
    Yiming Liang, Tianhan Xu and Yuta Kikuchi
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
    [Paper] [Project page]

  • Rethinking Directional Parameterization in Neural Implicit Surface Reconstruction
    Zijie Jiang, Tianhan Xu and Hiroharu Kato
    In European Conference on Computer Vision (ECCV), 2024.
    [Paper] [Project page]

  • Deforming Radiance Fields with Cages
    Tianhan Xu and Tatsuya Harada
    In European Conference on Computer Vision (ECCV), 2022.
    [Paper] [Project page] [BibTex]

  • Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis
    Tianhan Xu, Yasuhiro Fujita and Eiichi Matsumoto
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
    [Paper] [Project page] [Video] [BibTex]

  • Graph Stacked Hourglass Networks for 3D Human Pose Estimation
    Tianhan Xu and Wataru Takano
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
    [Paper] [BibTex]

Employment

  • Preferred Networks, Inc.
    • Researcher, Apr. 2023 – Present
    • Part-time Engineer, Oct. 2021 – Jan. 2022
    • Research Intern, Aug. 2021 – Oct. 2021
  • Woven by Toyota
    • Research Intern, Aug. 2022 – Dec. 2022

Education

  • Apr. 2025 – Present, Ph.D student, The University of Tokyo
  • Apr. 2021 – Mar. 2023, M.S., The University of Tokyo
  • Apr. 2017 – Mar. 2021, B.E., Osaka University