Jiayi Wu

Jiayi Wu

University of Florida

👤 Short Bio

Jiayi Wu is a member of the RoboPI lab, he is a master’s student(thesis) in ECE Department of the University of Florida. His research focus is on low-cost 3D reconstruction and depth estimation in scattering medium. He is currently working on wraping up his master thesis project under the supervision of Prof. Islam. The primaly research goal of his thesis is to formulate a fast and robust underwater 3D reconstruction algorithm based on the fusion of SfM algorithm and deep learning. He is also collaboraing with other students across the lab to make it lightweight and deployable on low-power robotic systems. .

My research interest includes:

  • General Environment Vision: Make computer vision systems more robust to the environment (scattering media, bad weather)
  • Low-cost 3D reconstruction and depth estimation in scattering medium
  • The application of computer vision in the medical field (including but not limited to medical image processing, pathological image segmentation, image enhancement)
  • AI-based Surgical Navigation: Make AI have the ability to generate structured diagnostic reports through medical images, and combine NLP algorithms and computer vision technology to achieve surgical navigation
  • Surgical robot: Enable surgical robots to have accurate multi-modal fusion perception ability and precise motion control and can perform precise surgery according to the instructions analyzed by doctors or AI

Latest CV’s link

📰 News

🎓 Educations

University of Florida

  • M.S.(Thesis) in Electrical and Computer Engineering ——— Aug. 2021- Present
    Supervised by Prof. Islam.

Zhejiang Sci-Tech University (ZSTU)

  • B.E. in Mechatronic Engineering ——— Sept. 2017- Jun. 2021
    2021 Outstanding Graduate, Zhejiang Sci-Tech University

📝 Publications

Conference Papers

ICRA 2023 (has been accepted)
sym
  • Yu, Boxiao, Wu, Jiayi, Islam, Md Jahidul. UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robots. ICRA. 2023, 10.48550/ARXIV.2209.12358
    [arXiv] [Code] [pre-print]

📃 Projects

A Collaborative Project
sym

UDepth

  • A monocular underwater depth estimation pipeline, using RMI as the input space, constructs a lightweight domain projection module, a lightweight CNN feature extraction module, and a lightweight Transformer-based depth estimation network. And the depth estimation network is supervised with knowledge of underwater light attenuation as a prior. The results show that our depth estimation accuracy is close to the SOTA model, and much faster than them.
    This is a collaborative project on underwater depth estimation with Boxiao Yu, a Ph.D. student in RoboPI lab.
    [arXiv] [Code] [pre-print]
Master's Thesis
sym

FSDU-SfM

  • A fast depth-guided semi-dense underwater 3D reconstruction pipeline without a deep learning model. Underwater image restoration is implemented through RMI channel and underwater imaging model to improve the number of feature matches. Reduce the computational complexity of feature extraction by using the depth map as a mask. In order to achieve higher quality(semi-dense) underwater 3D reconstruction, the depth maps are used as the supervision to refine the 3D point cloud and remove noise.
    This project is my master’s thesis, the overall framework has been determined, and most of the subsystems have obtained good results. It is expected that the project will be completed and submitted to IROS in Spring 2023.
R&D Internship Project
sym

Learning-based Infringing Video Retrieval

  • An learning-based infringing video retrieval system based on the fusion of global features and local features. I did a summer internship in the Vobile’s R&D department under the supervision of Dr. Zhao, CTO of Vobile. I built a learning-based infringing video retrieval system based on the fusion of global features and local features. I used Vobile’s video database to train the model, and achieved good performance. Before I ended my internship, I put it together into a python package and organize each component in the system into an easy-to-use python toolkit. I also wrote the manual of the package and a document about future optimization steps to finally handed over to the person who took over the project.

🏭 Job Experience

  • Digital Audio and Video Algorithm Engineer ——— May. 2022- Aug. 2022
    Vobile, Santa Clara, CA, United States.

  • Graduate Student Assistant ——— Jan. 2022- present
    Remote Sensing Laboratory at University of Florida, Gainesville, FL, United States.

🏅 Honors and Awards

SCHOLARSHIPS

  • 2020.12 Zhejiang Government Scholarship
  • 2019.09 First Class School Financial Aid for Overseas Exchange Program
  • 2018.12 Zhejiang Government Scholarship

COMPETITIONS

  • 2021.06 Individual 1st Prize in the National University Graduate Design Competition (Only two people won this award nationwide) 06/2021
  • 2019.10 Provincial 1st Prize of National 3D Digital Innovative Design Competition
  • 2019.09 2nd Prize of National 3dds Competition Classic
  • 2019.06 3rd Prize of The 16th Zhejiang Province Mechanical Design Competition for College Student
  • 2019.04 3rd Prize of The Challenge Cup Extracurricular Academic Works Competition

💬 Academic Services

Reviewer

  • 2023 IEEE International Conference on Robotics and Automation (ICRA)