News
02/2025 1 paper has been accpted to CVPR 2025.
06/2024 1 paper has been accpted to INTERSPEECH 2024.
Your browser does not support the video tag.
Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics
Lee Chae-Yeon* ,
Oh Hyun-Bin *,
Han EunGi ,
Kim Sung-Bin ,
Suekyeong Nam ,
Tae-Hyun Oh
CVPR , 2025
project page
/
arXiv
/
code
We define three essential criteria with evaluation metrics for perceptually accurate 3D talking heads and enhance existing models across these three aspects.
Your browser does not support the video tag.
MultiTalk: Enhancing 3D Talking Head Generation
Across Languages with Multilingual Video Dataset
Kim Sung-Bin *,
Lee Chae-Yeon* ,
Gihun Son*,
Oh Hyun-Bin ,
JangHoon Ju,
Suekyeong Nam ,
Tae-Hyun Oh
INTERSPEECH , 2024
project page
/
arXiv
/
code
/
dataset
We generate a 3D talking head with enhanced performance on multilingual speech.
Your browser does not support the video tag.
COARA: Efficient Correlation-Aware Uncertainty Modeling
in Hand Pose Estimation
Lee Chae-Yeon* ,
Nam Hyeon-Woo *,
Tae-Hyun Oh
Under Review
We estimate 3D hand pose uncertainty while maintaining robust performance.
Research Experiences
POSTECH - Advanced Machine Intelligence Lab , Pohang, Korea.Mar 2024 - Present
   Graduate Student, working with Tae-Hyun Oh .
This website is based on Jon Barron's website . I appreciate him for kindly open-sourcing the source code.