Dongyeun Lee
I’m Research Scientist at Statistical Inference and Information Theory in Information & Electronics Research Institute, KAIST, where I work on computer vision and machine learning. I received M.S. degree at KAIST, under the supervision of Prof. Junmo Kim.
I’m highly interested in building real-world applicable ML systems. My research interests include computer vision and machine learning, particularly image & video synthesis. I currently focus on the following research areas:
- 3D-Aware Image Synthesis
- Neural Talking Head Synthesis
- Audio Driven Talking Head Synthesis
- Diffusion Models
Publications
-
RADIO: Reference-Agnostic Dubbing Video Synthesis [paper]
Dongyeun Lee*, Chaewon Kim*, Sangjoon Yu, Jaejun Yoo†, Gyeong-Moon Park†
WACV 2024 -
Training Cartoonization Network without Cartoon [paper]
Doyeon Kim, Dongyeun Lee, Donggyu Joo, Junmo Kim
ICIP 2023 -
Fix the Noise: Disentangling Source Feature for Controllable Domain Translation [paper] [code]
Dongyeun Lee, Jae Young Lee, Doyeon Kim, Jaehyun Choi, Jaejun Yoo, Junmo Kim
CVPR 2023 -
Fix the Noise: Disentangling Source Feature for Transfer Learning of StyleGAN [paper]
Dongyeun Lee, Jae Young Lee, Doyeon Kim, Jaehyun Choi, Junmo Kim
CVPRW 2022 (AI for Content Creation, Best Paper Award, 2.56%)
Work Experiences
-
Research Scientist, Statistical Inference and Information Theory in Information & Electronics Research Institute, KAIST, Daejeon, South Korea, Apr. 2024 - Current
- AI Researcher, Klleon AI Research, Seoul, South Korea, May. 2022 - Mar. 2024
- Audio Driven Talking Head Synthesis
- Explicit Controllable 3D-Aware Talking Head Synthesis
- Research Intern, Vision and Learning Laboratory, KAIST, Daejeon, South Korea, Jan. 2020 - Jun. 2020
- Makeup Style Transfer
- Research Intern, Dabeeo, Seoul, South Korea, Apr. 2019 - Aug. 2019
- Arial Image Change Detection and Object Detection
Education
-
M.S. in Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Mar. 2021 - Aug. 2022
-
B.S. in Computer Science, Korea Advanced Institute of Science and Technology (KAIST), Mar. 2016 - Feb. 2021
Awards
- Best Paper Award, CVPR 2022 Workshops on AI for Content Creation, 1500$ Sponsored by Google