Scholar
kwan yun
Google Scholar ID: gpT9hDoAAAAJ
KAIST
Citations & Impact
Citations
34
H-index
4
i10-index
1
Publications
9
Co-authors
0
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation, PG, 2025; CGF
- AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models, CVPR, 2025
- FFaceNeRF: Few-shot Face Editing in Neural Radiance Fields, CVPR, 2025
- Representative Feature Extraction During Diffusion Process for Sketch Extraction with One Example, CVM (IF 18.3)
- LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example, CVPR, 2024
- Stylized Face Sketch Extraction via Generative Prior with Limited Data
Research Experience
- August 2025: Research on face editing was featured in KAIST News.
- June 2025: Presented two first-authored papers at CVPR 2025 as the only Korean researcher.
- March 2025: Gave an invited talk on graphics applications of generative models at Konyang University.
- July 2024: Received the Best Master’s Thesis Award from the Korea Computer Graphics Society.
Background
- Research Interests: Building human-centric generation models and leveraging them to animate and edit avatars. Background: Kwan Yun (윤관) has earned respect within Korea’s computer graphics and vision community through innovative work, particularly in animation technology.
Co-authors