| Wenjia Wang | 王文佳 |
I am a fourth-year (final-year) Ph.D. student in the Department of Computer Science at the University of Hong Kong, advised by Prof. Taku Komura.
During my Ph.D., I worked closely with Dr. Lei Yang and Dr. Jingbo Wang. I also collaborated with Dr. Rishabh Dabral and Prof. Christian Theobalt at the Max Planck Institute for Informatics.
My research focuses on Real2Sim and Sim2Real for embodied agents. In Real2Sim, I aim to leverage spatial intelligence models with affordable sensing systems to address generalizable human and scene understanding, enabling the acquisition of high-quality, simulation-ready data without tele-operation. In Sim2Real, I am interested in developing behavior foundation models for robust humanoid motor control, while using world models toward more general intelligence for humanoid robots.
Recent News
- Mar 10, 2026 [Open Source] Open-sourced EmbodMocap.
- Feb 22, 2026 [Accept] EmbodMocap accepted to CVPR 2026.
- Jan 6, 2026 [Project Page] Project page online for EmbodMocap.
- Jan 6, 2026 [Preprint] EgoGrasp preprinted on arXiv.
Selected Papers
EmbodMocap CVPR 2026
In-the-wild 4D human-scene reconstruction for embodied agents.
SIMS ICCV 2025
Simulating stylized human-scene interactions with retrieval-augmented script generation.
Zolly ICCV 2023, Oral 🏆️
Zoom focal length correctly for perspective-distorted human mesh reconstruction.
Research Scope
\
Openings / Collaboration
I am on the 2026 job market and am actively seeking research positions in industry or academia. Our group is also open to research collaborations and student projects related to the topics above. If you are interested in collaboration, please email me at wwj2022@connect.hku.hk.
Academic Services
- Teaching Assistant: COMP7404C (Spring 2024, HKU); COMP3329 (Spring 2024, HKU)
- Conference Reviewer: ICCV (2023); ICLR (2024–2026); ACCV (2024); SIGGRAPH Asia (2024–2025); CVPR (2025–2026); 3DV (2025–2026); ECCV (2026); SIGGRAPH (2026). Journal Reviewer: IEEE TIP (2022).