avatar

Chao Wang

AI Research Engineer
Meta Reality Labs
chaowang15 (at) gmail.com


About Me

I am a research engineer in the XR-Tech 3D GenAI team at Meta Reality Labs. Prior to joining Meta, I was a research engineer in the Intelligent Creation Lab at Bytedance / TikTok based in San Jose, CA, USA. Prior to that, I was a computer vision engineer at Matterport working on large scale high-quality 3D scene reconstruction and indoor touring. I graduated with my Ph.D. degree from Computer Science Department at the University of Texas at Dallas, under supervision of Prof. Xiaohu Guo. Before that, I graduated with my master degree in computer science from School of Software under supervision of Prof. Yu-shen Liu and Prof. Jun-hai Yong, and my bachelor degree from Department of Automation, both at Tsinghua University.

My current research interests are mainly in 3D GenAI area now, specifically on 3D model and animation generation. Previously I was focused on talking head generation, human video generation, multi-modal motion synthesis and generative modeling.

Work Experience

Education

Publications

  1. Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset
    Vasu Agrawal, ..., Chao Wang, ..., Michael Zollhoefer (long author list in alphabetical order), Meta AI
    Arxiv Preprint, 2025/07
    PDF Code Project BibTex Technical Report

  2. X-Dancer: Expressive Music to Human Dance Video Generation
    Zeyuan Chen, Hongyi Xu, Guoxian Song, You Xie, Chenxu Zhang, Xin Chen, Chao Wang, Di Chang, Linjie Luo
    The International Conference on Computer Vision (ICCV), 2025
    PDF Code Project BibTex Accepted

  3. X-Dyna: Expressive Dynamic Human Image Animation
    Di Chang, Hongyi Xu*, You Xie*, Yipeng Gao*, Zhengfei Kuang*, Shengqu Cai*, Chenxu Zhang*, Guoxian Song, Chao Wang, Yichun Shi, Zeyuan Chen, Shijie Zhou, Linjie Luo, Gordon Wetzstein, Mohammad Soleymani (*Equal contribution as second authors)
    IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
    PDF Code Project BibTex CVPR Highlight

  4. MagicTalk: Implicit and Explicit Correlation Learning for Diffusion-based Emotional Talking Face Generation (known as DREAM-Talk)
    Chenxu Zhang*, Chao Wang*, Jianfeng Zhang, Hongyi Xu, Guoxian Song, You Xie, Linjie Luo, Yapeng Tian, Xiaohu Guo, Jiashi Feng (*Equal contribution as first authors)
    Computational Visual Media (CVM), 2025
    PDF Code Project BibTex Oral

  5. X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention
    You Xie, Hongyi Xu, Guoxian Song, Chao Wang, Yichun Shi, Linjie Luo
    SIGGRAPH 2024
    PDF Code Project BibTex Video Oral

  6. DR2: Disentangled Recurrent Representation Learning for Data-efficient Speech Video Synthesis
    Chenxu Zhang, Chao Wang, Yifan Zhao, Shuo Cheng, Linjie Luo, Xiaohu Guo
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
    PDF BibTex Supplement Video Poster Poster

  7. Using Augmented Face Images to Improve Facial Recognition Tasks
    Shuo Cheng, Guoxian Song, Wan-Chun Ma, Chao Wang, Linjie Luo
    AI-Generated Characters: Putting Deepfakes to Good Use (CHI Workshop), 2022
    PDF Project BibTex Oral

  8. Study of detecting behavioral signatures within DeepFake videos
    Qiaomu Miao, Sinhwa Kang, Stacy Marsella, Steve DiPaola, Chao Wang, Ari Shapiro
    Arxiv Preprint, 2022
    PDF BibTex Video

  9. Efficient Plane-Based Optimization of Geometry and Texture for Indoor RGB-D Reconstruction
    Chao Wang, Xiaohu Guo
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019
    PDF Code Project BibTex Slides Oral

  10. Plane-based optimization of geometry and texture for RGB-D reconstruction of indoor scenes
    Chao Wang, Xiaohu Guo
    International Conference on 3D Vision (3DV), 2018
    PDF Code BibTex Video Slides Poster Oral

  11. Feature-based RGB-D camera pose optimization for real-time 3D reconstruction
    Chao Wang, Xiaohu Guo
    Computational Visual Media (CVM), 2017
    PDF BibTex Video Slides Oral

  12. Spectral animation compression
    Chao Wang, Yang Liu, Xiaohu Guo, Zichun Zhong, Binh Le, Zhigang Deng
    Computational Visual Media (CVM), 2015
    PDF BibTex Video Slides Oral

  13. Robust shape normalization of 3D articulated volumetric models
    Chao Wang, Yu-Shen Liu, Min Liu, Jun-Hai Yong, Jean-Claude Paul
    Computer-Aided Design (CAD), 2012
    PDF BibTex

Services

Conference Reviewers

Journal Reviewers

Side Projects