WindVChen

Computer Vision Researcher

[WindVChen @WindVChen]

📢V2M4 (Accepted by ICCV 2025)

We reconstruct 4D mesh animations from a single video with consistency in pose, appearance, topology, and texture.

project: https://t.co/nRbiSJXZSW
arxiv: https://t.co/VVAFUuZJwA

Collaboration with @_BiaoZhang , Xiangjun Tang and @peter_wonka

[WindVChen @WindVChen]

👋 Introducing - Zero-Shot Image Harmonization with Generative Model Prior👋

Paper: https://t.co/5bDNALQ1BL
Github: https://t.co/2nsdsvI0I5

Inspired by Human Behavior, we propose a Zero-Shot harmonization method based on Diffusion Models.😎🤗

[WindVChen @WindVChen]

Check out our DEMO video here! https://t.co/5zAV6OUMk4 Hope you enjoy and feel free to play around it!

[WindVChen @WindVChen]

Check our Demo video! Feel free to play aroumd it!

[WindVChen @WindVChen]

🌟 Introducing - Dense Pixel-to-Pixel Harmonization via Continuous Image Representation 🌟

Paper: https://t.co/B353JRWHts
Github: https://t.co/AWmoY2IMzs
Demo: https://t.co/2vAFfMLvma

Embrace the freedom to harmonize images with ANY Aspect Ratio and Resolution!🚀🖼

[WindVChen @WindVChen]

Check our Demo video! Feel free to play aroumd it!