Skip to content
View WindVChen's full-sized avatar
✍️
✍️

Highlights

  • Pro

Block or report WindVChen

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
WindVChen/README.md

👋 About Me (CV)

I received my master's degree at LEVIR Group, Beihang University (BUAA) in January 2024, supervised by Prof. Zhenwei Shi and Prof. Zhengxia Zou. Previously, I received my bachelor’s degree from Beihang University in June 2021. Besides that, I was also a research intern at SenseTime working on content generation from May - Aug, 2023, supervised by Dr. Jianlou Si. My current research interests lie in 4D (human motion) generation, AISafety, image synthesis, and remote sensing image processing.

📎 Homepages

🔥 News

  • 2024.10: One paper is accepted by TPAMI (IF=20.8)!
  • 2024.07: One paper is accepted by TGRS (IF=7.5)!
  • 2024.05: One paper is accepted by TGRS (IF=7.5)!
  • 2024.01: One paper is accepted by ICLR 2024 (Spotlight)!
  • 2023.12: One paper is accepted by TGRS (IF=7.5)!
  • 2023.10: One paper is accepted by TCSVT (IF=8.3)!
  • 2023.09: One paper is accepted by TGRS (IF=7.5)!
  • 2023.07: We have released Gradio Demo of our INR-Harmonization in Huggingface Space. Feel free to play around it 🎉🎉!
  • 2023.06: One paper is accepted by MICCAI (STAR Award)!
  • 2023.05: Honored to be invited to give talks about Diffusion Editing and Harmonization for OPPO Research Institute!
  • 2023.05: One paper is accepted by TGRS (IF=7.5)!
  • 2023.02: 1/2 papers are accepted by CVPR 2023, and one paper is accepted by CBM (IF=7.0)!
  • 2022.12: One paper is accepted by GRSL (IF=4.0)!
  • 2022.07: One paper is accepted by TGRS (IF=7.5)!
  • 2022.06: One paper is accepted by TGRS (IF=7.5)!
  • 2022.05: Achieve the 5th place in Track I: Classification Task Defense and the 6th place in Track II: Open Set Defense, CVPR 2022 Robust Models towards Open-world Classification 🎉🎉!

Pinned Loading

  1. Sitcom-Crafter Sitcom-Crafter Public

    A system for generating diverse, physically compliant 3D human motions across multiple motion types, guided by plot contexts to streamline creative workflows in anime and game design.

    Python 17 3

  2. VCO-AP VCO-AP Public

    A novel physical adversarial attack tackling the Digital-to-Physical Visual Inconsistency problem.

    Python 10

  3. DiffAttack DiffAttack Public

    An unrestricted attack based on diffusion models that can achieve both good transferability and imperceptibility.

    Python 166 17

  4. Diff-Harmonization Diff-Harmonization Public

    A novel zero-shot image harmonization method based on Diffusion Model Prior.

    Python 113 8

  5. INR-Harmonization INR-Harmonization Public

    A novel image harmonization method based on Implicit Neural Representation.

    Python 63 5

  6. LEVIR-Ship LEVIR-Ship Public

    This is the official release of LEVIR-Ship, which is a dataset for tiny ship detection under medium-resolution remote sensing images

    Python 79 7