Skip to content
View WindVChen's full-sized avatar
✍️
✍️
76 followers · 6 following

Achievements

Achievement: Pull SharkAchievement: Starstruckx2

Achievements

Achievement: Pull SharkAchievement: Starstruckx2

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to 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 am currently pursuing a Ph.D. at King Abdullah University of Science and Technology (KAUST) under the supervision of Prof. Peter Wonka, starting in August 2024. 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. Additionally, from Jan - Aug, 2024, I was remotely supervised by Prof. Xiaodan Liang on human motion generation. My current research interests lie in 4D reconstructiona and generation, AISafety, image synthesis, and remote sensing image processing.

📎 Homepages

🔥 News

  • 2026.05: Honored to receive the Outstanding Reviewer Award (Top 5%) of CVPR 2026!
  • 2026.04: One paper is accepted by CVPR 2026 (Oral, Top 3.4%)!
  • 2026.01: One paper is accepted by ICLR 2026!
  • 2025.06: One paper is accepted by ICCV 2025, and one paper is accepted by TIFS (IF=8.0)!!
  • 2025.01: One paper is accepted by ICLR 2025!
  • ... (For more news, please see personal page)

Pinned Loading

  1. PoseGAM PoseGAM Public

    A novel multi-view feedforward network that enables direct and robust object pose estimation from a query image.

    Python 18

  2. V2M4 V2M4 Public

    A novel 4D reconstruction method that directly generates high-quality, animation-ready 4D mesh asset (.GLB file) from a single monocular video.

    Python 128 4

  3. 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 80 7

  4. DiffAttack DiffAttack Public

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

    Python 264 21

  5. Diff-Harmonization Diff-Harmonization Public

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

    Python 150 12

  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 102 10