About

Hi! I'm a Research Scientist at Meta Reality Labs, building real-time multimodal models for human–AI collaboration and human–computer interaction on AI glasses and AR/VR.

I led Microgesture — the gesture recognition system on Quest headsets, featured at the Meta Connect keynote. I'm passionate about building intelligent agents that perceive human intent through multimodal signals, making collaboration with AI as natural as conversation.

Before joining Meta, I completed my PhD at ETH Zürich (2019), advised by Prof. Luc Van Gool and Prof. Angela Yao, where I studied 3D hand pose estimation and skeleton-based action recognition.

Selected Publications
  • LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion
    Muchen Li, Sammy Christen, Chengde Wan, Yujun Cai, Renjie Liao, Leonid Sigal, Shugao Ma
    CVPR 2025
    [pdf]
  • STMG: A Machine Learning Microgesture Recognition System for Supporting Thumb-Based VR/AR Input
    Kenrick Kin, Chengde Wan, Ken Koh, Andrei Marin, Necati Cihan Camgöz, Yubo Zhang, Yujun Cai, Fedor Kovalev, Moshe Ben-Zacharia, Shannon Hoople, Marcos Nunes-Ueno, Mariel Sanchez-Rodriguez, Ayush Bhargava, Robert Wang, Eric Sauser, Shugao Ma
    CHI 2024
    [pdf]
  • POET: Prompt Offset Tuning for Continual Human Action Adaptation Oral
    Prachi Garg, KJ Joseph, Vineeth N Balasubramanian, Necati Cihan Camgöz, Chengde Wan, Kenrick Kin, Weiguang Si, Shugao Ma, Fernando De la Torre
    ECCV 2024
    [pdf] [code]
  • Data-Free Class-Incremental Hand Gesture Recognition
    Shubhra Aich, Jesus Ruiz-Santaquiteria, Zhenyu Lu, Prachi Garg, KJ Joseph, Alvaro Fernandez Garcia, Vineeth N Balasubramanian, Kenrick Kin, Chengde Wan, Necati Cihan Camgöz, Shugao Ma, Fernando De la Torre
    ICCV 2023
    [pdf] [code]
  • PressureVision: Estimating Hand Pressure from a Single RGB Image
    Patrick Grady, Chengcheng Tang, Samarth Brahmbhatt, Christopher D. Twigg, Chengde Wan, James Hays, Charles C. Kemp
    ECCV 2022
    [pdf] [project]
  • MegaTrack: Monochrome Egocentric Articulated Hand-Tracking for Virtual Reality
    Shangchen Han, Beibei Liu, Randi Cabezas, Christopher D. Twigg, Peizhao Zhang, Jeff Petkau, Tsz-Ho Yu, Chun-Jung Tai, Muzaffer Akbay, Zheng Wang, Asaf Nitzan, Gang Dong, Yuting Ye, Lingling Tao, Chengde Wan, Robert Wang
    SIGGRAPH 2020
    [pdf] [project]
  • Dual Grid Net: Hand Mesh Vertex Regression from Single Depth Maps
    Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
    ECCV 2020
    [pdf]
  • Self-Supervised 3D Hand Pose Estimation Through Training by Fitting ★ Best Paper Final List
    Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
    CVPR 2019
    [pdf] [code]
  • Dense 3D Regression for Hand Pose Estimation
    Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
    CVPR 2018
    [pdf] [code]
  • Deep Learning on Lie Groups for Skeleton-Based Action Recognition Spotlight
    Zhiwu Huang, Chengde Wan, Thomas Probst, Luc Van Gool
    CVPR 2017
    [pdf]
  • Crossing Nets: Combining GANs and VAEs with a Shared Latent Space for Hand Pose Estimation Spotlight
    Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao
    CVPR 2017
    [pdf] [code]