Guandao Yang

myself/prof_pic.jpeg

I’m a postdoctoral scholar at Stanford, working with Prof. Leonidas Guibas and Prof. Gordon Wetzstein. I earned my PhD at Cornell Tech, advised by Prof. Serge Belongie and Prof. Bharath Hariharan. During my doctoral studies, I interned at various industry labs, including NVIDIA, Intel, and Google. Prior to my PhD, I received my Bachelor’s degree from Cornell University in Ithaca, majoring in Mathematics and Computer Science.

My research is dedicated to developing Artificial Shape Intelligence (ASI). Specifically, I’m interested in building ASIs that can create, edit, and analyze geometries for both virtual and physical world applications, which usually requires integration of advancements in computer vision, graphics, and machine learning.

Outside of academia, I like traditional rock climbing and playing classical piano.

News

Jul 01, 2024 BlenderAlchemy, PhysAvatar, and MegaScenes are accepted to ECCV!
Mar 23, 2024 One paper accepted to SIGGRAPH!
Feb 26, 2024 Two papers accepted to CVPR! See you in Seattle!

Selected works

  1. blenderalchemy.gif
    BlenderAlchemy: Editing 3D Graphics with Vision-Language Models
    Ian Huang, Guandao Yang, and Leonidas Guibas
    ECCV, 2024
  2. physavatar.gif
    PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
    Yang Zheng*, Qingqing Zhao*, Guandao Yang, Wang Yifan, Donglai Xiang, Florian Dubost, Dmitry Lagun, Thabo Beeler, Federico Tombari, Leonidas Guibas, and Gordon Wetzstein
    ECCV, 2024
  3. MegaScenes_teaser.jpg
    MegaScenes: Scene-Level View Synthesis at Scale
    Joseph Tung, Gene Chou, Ruojin Cai, Guandao Yang, Kai Zhang, Gordon Wetzstein, Bharath Hariharan, and Noah Snavely
    ECCV, 2024
  4. gpt4eval.jpeg
    GPT-4V (ision) is a Human-Aligned Evaluator for Text-to-3D Generation
    Tong Wu*, Guandao Yang*, Zhibing Li*, Kai Zhang, Ziwei Liu, Leonidas Guibas, Dahua Lin, and Gordon Wetzstein
    In CVPR , 2024
  5. mcgpnf.jpg
    Neural Caches for Monte Carlo Partial Differential Equation Solvers
    Zilu Li*, Guandao Yang*, Xi Deng, Christopher De Sa, Bharath Hariharan, and Steve Marschner
    In SIGGRAPH Asia Conference , 2023
  6. pnf.gif
    Polynomial neural fields for subband decomposition and manipulation
    Guandao Yang*, Sagie Benaim*, Varun Jampani, Kyle Genova, Jonathan Barron, Thomas Funkhouser, Bharath Hariharan, and Serge Belongie
    NeurIPS, 2022
  7. NFGP.png
    Geometry processing with neural fields
    Guandao Yang, Serge Belongie, Bharath Hariharan, and Vladlen Koltun
    NeurIPS, 2021
  8. ShapeGF.gif
    Learning gradient fields for shape generation
    Ruojin Cai*, Guandao Yang*, Hadar Averbuch-Elor, Zekun Hao, Serge Belongie, Noah Snavely, and Bharath Hariharan
    In ECCV (Spotlight) , 2020
  9. pointflow.gif
    Pointflow: 3d point cloud generation with continuous normalizing flows
    Guandao Yang*, Xun Huang*, Zekun Hao, Ming-Yu Liu, Serge Belongie, and Bharath Hariharan
    In ICCV (Oral) , 2019