Bio

I am building something new in stealth-mode, focused on Physical AI. Previously, I was an AI Research Scientist at Meta working on foundation models for 3D/4D vision and video generation.

I received my Ph.D. degree from ETH Zurich under the supervision of Prof. Otmar Hilliges and Prof. Marc Pollefeys. I was supported by the Microsoft Swiss JRC PhD Fellowship, through which I collaborated closely with Dr. Julien Valentin.

During my Ph.D., I was a research intern at Meta, mentored by Prof. Yaser Sheikh. After my Ph.D., I worked as a Senior Researcher/Postdoc at ETH Zurich for three months.

I received my master's degree in Robotics, Systems and Control from ETH Zurich with distinction, under the supervision of Prof. Luc Van Gool, and my bachelor's degree in Electrical Engineering and Information Technology from University of Stuttgart and Wuhan University.

Open to collaboration Always happy to connect, collaborate, or exchange research ideas. Feel free to reach out.

News

I gave a guest lecture for the Virtual Humans: Foundations and Applications course at Westlake University.
I was honored to be recognized again as an Outstanding Reviewer at CVPR2026!
Gaussian Wardrobe is accepted by 3DV2026.
I successfully defended my Ph.D. degree! My thesis Human Digitization from In-the-Wild Videos is now available online.
PHD is accepted by ICCV2025.
I was honored to be recognized as an Outstanding Reviewer at CVPR2025!
Vid2Avatar-Pro is accepted by CVPR2025.
ReLoo and HSR are accepted by ECCV2024.
I started my research internship at Meta in Pittsburgh.
MultiPly and 4D-DRESS are accepted by CVPR2024.
EMDB is accepted by ICCV2023.
Vid2Avatar, X-Avatar and Hi4D are accepted by CVPR2023.
I started my Ph.D. study at ETH Zurich.

Publications

* Equal Contribution. † Equal Advisory / Corresponding Author. ‡ Project Lead.

World Models & Embodied AI

Perceive, Predict, and Plan: A Unified World Action Model for Egocentric Dexterous Manipulation
arXiv 2026
Zirui Wu, Chen Guo‡, Tianjian Jiang, Zeren Jiang, Zeming Li, Lingchen Yang, Longteng Duan, Ying Xue, Handi Yin, Shenyuan Gao, Martin R. Oswald, Jun Zhang, Ping Tan†, Jie Song†
Project page Paper Video
World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models
arXiv 2026
Junyi Wu*, Zekun Li*, Chenhongyi Yang, Chen Guo, Lingchen Yang, Yongan Zhang, Xinyi Zhang, Hongbing Hu, Bartek Rymkowski, Srinath Sridhar, Yan Yan, Xijie Huang
Project page Paper

Human-Centric 3D Reconstruction & Generation

Gaussian Wardrobe teaser
Gaussian Wardrobe: Compositional 3D Gaussian Avatars for Free-Form Virtual Try-on
3DV 2026
Zhiyi Chen*, Hsuan-I Ho*, Tianjian Jiang, Jie Song, Manuel Kaufmann, Chen Guo†
Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior
CVPR 2025
Chen Guo*, Junxuan Li*, Yash Kant, Yaser Sheikh, Shunsuke Saito†, Chen Cao†
Project page Video Paper Public Comparisons
ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild
ECCV 2024
Chen Guo*, Tianjian Jiang*, Manuel Kaufmann, Chengwei Zheng, Julien Valentin, Jie Song†, Otmar Hilliges
Project page Code Video Paper
Vid2Avatar teaser
Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition
CVPR 2023
Chen Guo, Tianjian Jiang, Xu Chen, Jie Song†, Otmar Hilliges
Project page Code Video Paper
X-Avatar teaser
X-Avatar: Expressive Human Avatars
CVPR 2023
Kaiyue Shen*, Chen Guo*, Manuel Kaufmann, Juan Zarate, Julien Valentin, Jie Song†, Otmar Hilliges
Project page Code Video Paper
PINA teaser
PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence
CVPR 2022
Zijian Dong*, Chen Guo*, Jie Song†, Xu Chen, Andreas Geiger, Otmar Hilliges
Human Performance Capture teaser
Human Performance Capture from Monocular Video in the Wild
3DV 2021
Chen Guo, Xu Chen, Jie Song, Otmar Hilliges

3D Human Interaction

RHINO teaser
RHINO: Reconstructing Human Interactions with Novel Objects from Monocular Videos
CVPR 2026
Lixin Xue, Chengwei Zheng, Georgios Paschalidis, Chen Guo, Manuel Kaufmann, Juan Zarate, Dimitrios Tzionas
Project page Paper Supplementary
HSR teaser
HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos
ECCV 2024
Lixin Xue, Chen Guo, Chengwei Zheng, Fangjinhua Wang, Tianjian Jiang, Hsuan-I Ho, Manuel Kaufmann, Jie Song†, Otmar Hilliges
MultiPly teaser
MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild
CVPR 2024 Oral
Zeren Jiang*, Chen Guo*, Manuel Kaufmann, Tianjian Jiang, Julien Valentin, Otmar Hilliges, Jie Song†
Project page Code Video Paper
Hi4D teaser
Hi4D: 4D Instance Segmentation of Close Human Interaction
CVPR 2023
Yifei Yin, Chen Guo, Manuel Kaufmann, Juan Zarate, Jie Song, Otmar Hilliges

3D Human Perception & Understanding

PHD teaser
PHD: Personalized 3D Human Body Fitting with Point Diffusion
ICCV 2025
Hsuan-I Ho, Chen Guo, Po-Chen Wu, Ivan Shugurov, Chengcheng Tang, Abhay Mittal, Sizhe An, Manuel Kaufmann†, Linguang Zhang†
4D-DRESS teaser
4D-DRESS: A 4D Dataset of Real-World Human Clothing With Semantic Annotations
CVPR 2024 Highlight
Wenbo Wang*, Hsuan-I Ho*, Chen Guo, Boxiang Rong, Artur Grigorev, Jie Song, Juan Zarate†, Otmar Hilliges
EMDB teaser
EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild
ICCV 2023
Manuel Kaufmann, Jie Song, Chen Guo, Kaiyue Shen, Tianjian Jiang, Chengcheng Tang, Juan Zarate, Otmar Hilliges
Shape-aware Multi-Person Pose Estimation teaser
Shape-aware Multi-Person Pose Estimation from Multi-view Images
ICCV 2021
Zijian Dong, Jie Song, Xu Chen, Chen Guo, Otmar Hilliges