Chengan He

chengan [at] meta (dot) com|[CV]

profile.png

I’m a Research Scientist at Meta, working on human-centric computer graphics and vision problems. My research combines physical principles with data-driven learning to capture how humans look, move, and interact with the physical world. My earlier work also spanned human digitization, reflectance capture, and material appearance modeling.

Before joining Meta, I completed my Ph.D. in the Computer Graphics Group at Yale University, advised by Prof. Holly Rushmeier. Prior to Yale, I earned my bachelor’s degree from Zhejiang University, under the supervision of Prof. Hongzhi Wu.

💡 I'm open to research collaborations. If you see alignment in our research interests or wish to explore potential opportunities, feel free to email me directly.

News

Mar 31, 2025 One paper accepted to SIGGRAPH 2025 as a Journal Paper.
Jan 22, 2025 One paper accepted to ICLR 2025 as Spotlight.
Dec 06, 2024 Digital Salon was presented at SIGGRAPH Asia 2024 Real-Time Live! in Tokyo.
Oct 20, 2022 NeMF was involved in Project Motion Mix on Adobe Max Sneaks 2022.
Sep 14, 2022 One paper accepted to NeurIPS 2022 as Spotlight.

Publications

  1. CVPR
    Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
    Meta Codec Avatars Lab
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
  2. arXiv
    CamLit: Unified Video Diffusion with Explicit Camera and Lighting Control
    Zhiyi Kuang, Chengan He, Egor Zakharov, Yuxuan Xue, Shunsuke Saito, Olivier Maury, Timur Bagautdinov, Youyi Zheng, and Giljoo Nam
    Preprint (arXiv), 2026
  3. ICCV
    Augmented Mass-Spring Model for Real-Time Dense Hair Simulation
    Jorge Alejandro Amador Herrera, Yi Zhou, Xin Sun, Zhixin Shu, Chengan He, Sören Pirk, and Dominik L. Michels
    In IEEE/CVF International Conference on Computer Vision (ICCV), 2025
  4. SIGGRAPH
    3dgh.webp
    3DGH: 3D Head Generation with Composable Hair and Face
    Chengan He, Junxuan Li, Tobias Kirschstein, Artem Sevastopolsky, Shunsuke Saito, Qingyang Tan, Javier Romero, Chen Cao, Holly Rushmeier, and Giljoo Nam
    ACM Transactions on Graphics (SIGGRAPH), 2025
  5. ICLR
    perm.webp
    Perm: A Parametric Representation for Multi-Style 3D Hair Modeling
    Chengan He, Xin Sun, Zhixin Shu, Fujun Luan, Sören Pirk, Jorge Alejandro Amador Herrera, Dominik L. Michels, Tuanfeng Y. Wang, Meng Zhang, Holly Rushmeier, and Yi Zhou
    In International Conference on Learning Representations (ICLR), 2025 Spotlight
  6. SIGGRAPH Asia
    digital-salon.webp
    Digital Salon: An AI and Physics-Driven Tool for 3D Hair Grooming and Simulation
    Chengan He*, Jorge Alejandro Amador Herrera*, Yi Zhou*, Zhixin Shu, Xin Sun, Yao Feng, Sören Pirk, Dominik L. Michels, Meng Zhang, Tuanfeng Y. Wang, and Holly Rushmeier
    In SIGGRAPH Asia 2024 Real-Time Live! (SIGGRAPH Asia), 2024
  7. NeurIPS
    NeMF: Neural Motion Fields for Kinematic Animation
    Chengan He, Jun Saito, James Zachary, Holly Rushmeier, and Yi Zhou
    In Advances in Neural Information Processing Systems (NeurIPS), 2022 Spotlight
  8. SIGGRAPH
    multi-ipm.webp
    An Inverse Procedural Modeling Pipeline for SVBRDF Maps
    Yiwei Hu, Chengan He, Valentin Deschaintre, Julie Dorsey, and Holly Rushmeier
    ACM Transactions on Graphics (SIGGRAPH), 2022
  9. SIGGRAPH Asia
    jointcap.webp
    Learning efficient illumination multiplexing for joint capture of reflectance and shape
    Kaizhang Kang, Cihui Xie, Chengan He, Mingqi Yi, Minyi Gu, Zimin Chen, Kun Zhou, and Hongzhi Wu
    ACM Transactions on Graphics (SIGGRAPH Asia), 2019