Youkang Kong

Chinese - 孔佑康

my.jpg

I am a Ph.D. student in Computer Science at Tsinghua University, affiliated with the Institute for Advanced Study, and advised by Prof. Heung-Yeung Shum. Before joining Tsinghua, I received my B.Eng. in Computer Science from the Honors School of Harbin Institute of Technology, Harbin Institute of Technology in 2021.

I have been a research intern at Microsoft Research Asia since 2020, where I work with Dr. Yang Liu, Dr. Yue Dong and Dr. Xin Tong on 3D-related research problems.

My primary research interests lie in computer graphics and 3D vision, with a focus on 3D generation, rendering, and modeling. I am particularly interested in building scalable and controllable methods for neural 3D content creation.

news

Apr 01, 2026 Two papers have been accepted to SIGGRAPH 2026.

publications

Featured papers are highlighted.

  1. squadgen.png
    SQuadGen: Generating Simple Quad Layouts via Chart Distance Fields
    Youkang Kong, Yang Liu, Yue Dong, Xin Tong, and Heung-Yeung Shum
    In SIGGRAPH, 2026
    Project Page Code
  2. caslayout.png
    CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling
    Yingrui Wu, Youkang Kong, Mingyang Zhao, Weize Quan, Dongmin Yan, and 1 more author
    In SIGGRAPH, 2026
    Project Page Code
  3. DiLightNet-yellow.png
    DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation
    Chong Zeng, Yue Dong, Pieter Peers, Youkang Kong, Hongzhi Wu, and 1 more author
    In ACM SIGGRAPH 2024 Conference Papers, 2024
    arXiv Project Page Code
  4. multiview.png
    Multi-view representation is what you need for point-cloud pre-training
    Siming Yan, Chen Song, Youkang Kong, and Qixing Huang
    In ICLR, 2024
    arXiv
  5. neuralpath.png
    Neural Path Sampling for Rendering Pure Specular Light Transport
    Rui Yu, Yue Dong, Youkang Kong, and Xin Tong
    Computer Graphics Forum, 2024
    DOI
  6. TKDE
    Constrained Truth Discovery
    Chen Ye, Hongzhi Wang, Kangjie Zheng, Youkang Kong, Rong Zhu, and 2 more authors
    IEEE Transactions on Knowledge and Data Engineering, 2020
    DOI