Yingtian Liu (刘应天)

prof_pic.jpeg

I am currently a Research Scientist at VAST AI Research (VAIR), building Tripo.

My research interest is to enable machines to understand, reconstruct, and generate 2D/3D visual content from real-world data, with a focus on 3D mesh generation and vector font generation. Within these areas, I am especially interested on tasks on native 3D meshes, e.g. quad meshing, native mesh generation, native mesh texturing, UV unwrapping, etc.

I obtained my Ph.D. degree in Graphics & Geometric Computing Lab at Tsinghua University (THU) in 2025, supervised by Prof. Song-Hai Zhang. Prior to that, I received my B.S. degree from the Department of Computer Science and Technolog at Tsinghua University (THU) in 2020, co-supervised by Prof. Shi-Min Hu and Prof. Song-Hai Zhang.

Beyond research, I am also deeply interested in Origami (paper folding).

selected publications

  1. CVPR 2023
    dualvector.png
    Dualvector: Unsupervised vector font synthesis with dual-part representation
    Ying-Tian Liu, Zhifei Zhang, Yuan-Chen Guo, Matthew Fisher, Zhaowen Wang, and Song-Hai Zhang†
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
    arXiv Code
  2. Open Source Project
    threestudio.gif
    threestudio: A unified framework for 3d content generation
    Yuan-Chen Guo, Ying-Tian Liu, Ruizhi Shao, Christian Laforte, Vikram Voleti, Guan Luo, Chia-Hao Chen, Zi-Xin Zou, Chen Wang, Yan-Pei Cao, and others
    2023
    PDF Code
  3. CVPR 2024
    pi3d.png
    Pi3d: Efficient text-to-3d generation with pseudo-image diffusion
    Ying-Tian Liu, Yuan-Chen Guo, Guan Luo, Heyi Sun, Wei Yin, and Song-Hai Zhang†
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
    arXiv
  4. ACM TOG
    texgen.jpg
    TEXGen: a Generative Diffusion Model for Mesh Textures
    Xin Yu, Ze Yuan, Yuan-Chen Guo, Ying-Tian Liu, Jianhui Liu, Yangguang Li, Yan-Pei Cao, Ding Liang, and Xiaojuan Qi†
    ACM Transactions on Graphics (TOG), 2024
    Honorble Mention Award arXiv Code
  5. ICCV 2025
    neuframeq_sq.png
    NeuFrameQ: Neural Frame Fields for Scalable and Generalizable Anisotropic Quadrangulation
    Ying-Tian Liu, Jiajun Li, Yu-Tao Liu, Xin Yu, Yuan-Chen Guo, Yan-Pei Cao, Ding Liang, Ariel Shamir, and Song-Hai Zhang†
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025
    PDF Supp Website