Skip to content
View ZhenhuaDu11's full-sized avatar
🙃
Coding
🙃
Coding
3 followers · 74 following
  • National University of Defense Technology
  • Changsha, China
  • 07:27 (UTC +08:00)

Block or report ZhenhuaDu11

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ZhenhuaDu11/README.md

Hi there👋I'm Zhenhua Du

I'm currently a M.Eng. student at National University of Defense Technology (NUDT), supervised by Kai Huo and Shuaifeng Zhi. Before that, I also received my Bachelor's degree from NUDT in 2022.

🤗Research

My research interests lie in computer vision and robotics, with a current focus on scene reconstruction and semantic understanding. My ultimate goal is to develop spatial AI capable of autonomously exploring, understanding and interacting with the real world. To achieve this, my interest expands into the following areas:

  • Efficient representation, reconstruction and simulation of the visual world;
  • Open-vocabulary, hierarchical and interactive understanding of complex scenes;
  • Intelligent robotics applications (e.g., SLAM, navigation, manipulation) that are constrained by GPU power and real-time requirements.

Please feel free to contact me if you are interested in discussing these topics with me.

😎Outside of Research

  • I love photography, basketball, music and movies;
  • I like chatting with interesting people;
  • I enjoy reading and thinking.

Pinned Loading

  1. Awesome-Scene-Representations-and-Understandings Awesome-Scene-Representations-and-Understandings Public

    Awesome papers and resources focused on Scene Representation Learning and Semantic Scene Understanding.

  2. Mose Mose Public

    [RA-L 2024] MOSE: Monocular Semantic Reconstruction Using NeRF-Lifted Noisy Priors