Chenhao Zheng

I am a first year CS Ph.D. student at the University of Washington, advised by Prof. Ranjay Krishna. Before that, I was an undergraduate student at University of Michigan and Shanghai Jiao Tong University, where I was fortunate to also work with Prof. Andrew Owens and Dr. Adam Harley. I work on computer vision, with a particular interest in videos (video understanding, video->3d, video->robotics) and large vision-language models.

I am happy to collaborate with people and mentor a few students on research, feel free to drop me an email if you are interested in.

News

  • 2025-03: I will join Allen Institute of AI as a research scientist intern this summer.
  • 2025-02: "Synthetic Visual Genome" paper was accepted to CVPR 2025
  • 2024-08: "Acoustic volume rendering" paper was accepted to NeurIPS 2024 and selected as spolight.
  • 2024-02: "Iterated learning" paper was accepted to CVPR 2024.
  • 2024-01: Michigan football wins National Championship! Let's Go Blue!!!
  • 2023-12: Selected as Honorable Mention for 2024 CRA Outstanding Undergraduate Researcher Award in the United States.
  • Publications and preprints

    One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory
    Chenhao Zheng, Jieyu Zhang, Reza Salehi, Ziqi Gao, Vishnu Iyengar, Norimasa Kobori, Quan Kong, Ranjay Krishna
    In submission
    pdf comes soon
    Synthetic Visual Genome
    Jae Sung Park, Zixian Ma, Linjie Li, Chenhao Zheng, Cheng-Yu Hsieh, Ximing Lu, Khyathi Chandu, Quan Kong, Norimasa Kobori, Ali Farhadi, Yejin Choi, Ranjay Krishna
    CVPR, 2025
    pdf comes soon
    Acoustic Volume Rendering for Neural Impulse Response Field
    Zitong Lan, Chenhao Zheng, Zhiwei Zheng, Mingmin Zhao
    NeurIPS, 2024 (spotlight)
    paper / project page
    Iterated Learning Improves Compositionality in Large Vision-Language Models
    Chenhao Zheng, Jieyu Zhang, Aniruddha Kembhavi, Ranjay Krishna
    CVPR, 2024
    paper / project page / video
    EXIF as Language: Learning Cross-Modal Associations Between Images and Camera Metadata
    Chenhao Zheng, Ayush Shrivastav, Andrew Owens
    CVPR, 2023 (oral)
    paper / project page / video
    A-ESRGAN: Training Real-World Blind Super-Resolution with Attention U-Net Discriminators
    Zihao Wei, Yidong Huang, Yuang Chen, Chenhao Zheng, Jinnan Gao
    PRICAI, 2023
    project page / paper / bibtex

    Side projects

    Urban Rush: Making fitness fun with VR
    This project was done with Rahmy Salmon, Kalpit Haresh Sutariya, Akash Nallani and Ashish Patel. We develop immersive VR experiences aimed at encouraging exercise. Urban Rush lets the player to have fun in a narrative-based exploration while completing activities in a unique, procedurally generated city environment.
    project page
    CSE-Simulator
    This project was done with Rahmy Salmon and Kalpit Haresh Sutariya. We build an interactive computer lab simulator in VR using Unreal Engine. It also has a game mode where you can enjoy the same flying experience as Neo did in The Matrix movie.
    Demo video