Bridging 2D vision and 3D graphics to build human-centric generative models for controllable animation and high-fidelity synthesis
I started as a research intern at Microsoft Research Cambridge in May 2026.
Our work on stylization-agnostic facial identity recognition will appear in ACM Transactions on Graphics.
My research on face editing was featured in KAIST News.
I received the Best Master's Thesis Award from the Korea Computer Graphics Society.
Our work on animatable stylized face generation from one example, co-first-authored with Soyeon Yoon.
Scroll for earlier updates
Contact-guided retargeting of human-object interactions to diverse characters while preserving motion semantics and object contact.
Speech-driven 3D animation for arbitrary characters using video diffusion models, without requiring character animation data.
Stylization-Agnostic Identity Encoder.
Diffusion cross-attention for deepfake detection.
The first text generated stylized 3DMM.
AnyMoLe performs motion in-betweening for arbitrary characters only using inputs.
Mask-based 3D face editing using a customized layout, trained with few-shot learning..
Stylized and Animatable face mesh with one example.
Utilizing the generative feature to extract and edit face sketch.