Scholar
Sihun Cha
Google Scholar ID: gwSV7H4AAAAJ
KAIST
Citations & Impact
Citations
43
H-index
4
i10-index
2
Publications
15
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- One-shot Motion Personalization for Audio-driven Portrait Video Generation (In submission)
- Mesh Agnostic Audio-Driven 3D Facial Animation (KCGS 2025, Best Paper Award)
- SALAD: Skeleton-Aware Latent Diffusion for Text-driven Motion Generation and Editing (CVPR 2025)
- Neural Face Skinning for Mesh-agnostic Facial Expression Cloning (Eurographics 2025, Computer Graphics Forum)
- Deep Learning-Based Facial Retargeting Using Local Patches (Computer Graphics Forum)
- NeRFFaceSpeech: One-shot Audio-driven 3D Talking Head Synthesis via Generative Prior (CVPR Workshop 2024)
- LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example (CVPR 2024)
- Generating Texture for 3D Human Avatar from a Single Image using Sampling and Refinement Networks (Eurographics 2023, Computer Graphics Forum)
- Reference Based Sketch Extraction via Attention Mechanism (SIGGRAPH Asia 2022, ACM Transactions on Graphics)
- Generating 3D Human Texture from a Single Image with Sampling and Refinement (SIGGRAPH 2022 Posters)
- "Anyway," Two-player Defense Game via Voice Conversation (CHI Play 2021)
Research Experience
- Conducting doctoral research at the Visual Media Lab, KAIST.
Education
- Ph.D. at KAIST, Visual Media Lab, Advisor: Junyong Noh; B.A. in Fine Arts at Korea National University of Arts.
Background
- Research Interest: How to create and control 3D content intuitively; Current research focuses on generating and editing facial animation.
