avatar

Yan Zhang

Research Scientist
Meshcapade
yan@meshcapade.com


homepage at ETH Zurich

homepage at MPI Tuebingen

About Me

I am currently a machine learning scientist at Meshcapade, working on human foundation models and behavior computing. My researches have been covering human motion and behavior modeling, 3D human perception, generative models, etc., as well as their applications in mixed reality, embodied AI, architecture design, and others.

During 2020-2023, I was a postdoc researcher at VLG, ETH Zurich, supervised by Prof. Siyu Tang. I got my PhD degree at June 2020 from Ulm University, Germany, supervised by Prof. Heiko Neumann. During 2018-2020, I was a research intern at Max-Planck Institute for Intelligent Systems, working with Prof. Siyu Tang, Prof. Michael J. Black, and other PS folks. Please see more details in my CV.

News

Services

Chair & Review

Activities

Other Affiliations

Teaching

Co-supervised Student Projects at ETH Zurich

Lectures at ETH Zurich

Seminars at ETH Zurich

Recent Publications

    Please see the full publication list at Google Scholar
  1. CVPR
    Yan Zhang, Sergey Prokudin, Marko Mihajlovic, Qianli Ma, Siyu Tang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
    A compact implicit motion field with spatiotemporal regularity.
  2. CVPR
    Gen Li, Kaifeng Zhao, Siwei Zhang, Xiaozhong Lyu, Mihai Dusmanu, Yan Zhang, Marc Pollefeys, Siyu Tang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. (ORAL)
    Human motion synthesis with egocentric visual perception; Rendered synthetic data boosts several egocentric vision tasks.
  3. CVPR
    Ronghui Li, YuXiang Zhang, Yachao Zhang, Hongwen Zhang, Jie Guo, Yan Zhang, Yebin Liu, Xiu Li
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
    A two-stage coarse-to-fine diffusion architecture for extremely long dance generation; characteristic dance primitives.
  4. ICCV
    Kaifeng Zhao, Yan Zhang, Shaofei Wang, Thabo Beeler, Siyu Tang
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
    Generative motion pritimives + RL to synthesize lifelike behavior in 3D scenes.
  5. ICCV
    Siwei Zhang, Qianli Ma, Yan Zhang, Sadegh Aliakbarian, Darren Cosker, Siyu Tang
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023. (ORAL)
    A scene-conditioned diffusion model regresses 3D bodies from single images. The denoising process guided by COAP solves interpenetration.
  6. CVPR
    Yan Zhang, Siyu Tang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
    Generative motion pritimives + RL to synthesize locomotion behavior of diverse human identities. Featured at the homepage of ETH Zurich.
  7. CVPR
    Yan Zhang, Michael J. Black, Siyu Tang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
    A novel marker-based body representation for stochastic motion prediction.
  8. CVPR
    Yan Zhang, Mohamed Hassan, Heiko Neumann, Michael J Black, Siyu Tang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020 (ORAL) .
    generative model to populate scenes + test-time optimization
  9. CVPR
    Yan Zhang, Siyu Tang, Krikamol Muandet, Christian Jarvers, Heiko Neumann
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
    A novel plug-in bilinear pooling layer for fine-grained action segmentation.
  10. ECCV
    Siwei Zhang, Qianli Ma, Yan Zhang, Zhiyin Qian, Taein Kwon, Marc Pollefeys, Federica Bogo & Siyu Tang
    European Conference on Computer Vision (ECCV), 2022.
    A dataset of people interactions in 3D scenes, captured by Kinects and Hololens.
  11. ICCV
    Siwei Zhang, Yan Zhang, Federica Bogo, Marc Pollefeys, Siyu Tang
    IEEE/CVF International Conference on Computer Vision (ICCV), 2021 (ORAL) .
    Marker motion priors to capture body motions in 3D scenes.


Powered by Jekyll and Minimal Light theme.