|
Lee Chae-Yeon Hi! I'm a MS student at AMILab in Artificial Intelligence at POSTECH, advised by Tae-Hyun Oh. I am interested in 3D computer vision, cross-modal generation, and multi-modal learning, but not limited to. chaeyeon.lee@postech.ac.kr / CV / Scholar / LinkedIn / Github |
|
News
|
Publications |
|
Learning Correlation-aware Aleatoric Uncertainty for 3D Hand Pose Estimation
Lee Chae-Yeon, Nam Hyeon-Woo, Tae-Hyun Oh BMVC, 2025 project page / arXiv / code We introduce aleatoric uncertainty modeling into the 3D hand pose estimation framework, achieving a better trade-off between capturing joint correlation and efficiency. |
|
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 Highlight 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. |
|
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. |
Research Experiences
|
|
This website is based on Jon Barron's website. I appreciate him for kindly open-sourcing the source code. |