Serin Yoon

Hello! I recently completed my Master’s degree at GSCT KAIST, where I conducted research in the Visual Media Lab under the supervision of Prof. Junyong Noh. My research interests lie in Computer Graphics and Computer Vision, particularly focusing on 3D Character Animation. I am passionate about deriving meaningful insights and results through the use of geometric data.

Email  /  CV  /  Scholar  /  GitHub  /  LinkedIn

profile photo

Publications

Anymate: Animating Arbitrary 3D Faces from Video
First Author
In submission

An animating method that enables smooth and identity-preserving animation of arbitrary 3D faces from in-the-wild video.

AnyTalk: Speech Animation for Arbitrary Characters Leveraging a Video Generation Model
Co-First Author
In submission

A data-free method that generalizes realistic, lip-synced 3D speech animations for arbitrary characters using video diffusion models.

SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing
Seokhyeon Hong, Chaelin Kim, Serin Yoon, Junghyun Nam, Sihun Cha, Junyong Noh
CVPR 2025

A method that incorporates interactions between joints, frames, and words for text-driven motion generation and zero-shot editing.

Neural Face Skinning for Mesh-agnostic Facial Expression Cloning
Sihun Cha, Serin Yoon, Kwanggyoon Seo, Junyong Noh
Eurographics 2025, CGF

A method that enables direct retargeting between two facial meshes with different shapes and mesh structures.

Simulation Tool for Theatrical Scene Design Using Generative AI
Meongeun Kim*, Eunbyul Park*, Serin Yoon*, Jaehong Ahn (*equal contribution)
KCGS 2024 Poster Best Poster Award

Simulation tool that leverages Generative AI to assist in staging musical scenes by simulating stage direction and design.

Relative Depth-Based Oriental Black Ink Style Rendering
Minseong Kim, Serin Yoon, Sangmin Kim, Sungkil Lee
KCGS 2022 Poster

A rendering technique for generating ink-painting style edge images based on relative depth differences between object boundaries.

Edge Computing based Cloud Parking Management System
Gilhan Park, Heedong Kim, Serin Yoon, Jaehwan Lee, Soyeon Jeong
KIPS 2021

Edge-computing cloud system that automates tasks like entry/exit tracking and unauthorized parking detection.



Education

Korea Advanced Institute of Science & Technology
Master of Culture Technology (Advisor: Junyong Noh, GPA: 4.0/4.3)
Mar 2024 - Feb 2026
Sungkyunkwan University
Bachelor of Computer Science Education (GPA: 3.91/4.5)
Mar 2019 - Feb 2024


Experiences

Visual Media Lab
Student Researcher
Mar 2024 - Feb 2026
Mirim Girl's High School
Information Science Student Teacher
Apr 2023 - May 2023


Projects

Generating Hyper-Realistic to Extremely-stylized Face Avatar with Varied Speech Speed and Context-based Emotional Expression
Sep 2024 - Feb 2026

Development of customizable AI avatars that generate responsive, conversational facial animations, enabling lifelike interaction and feedback through intuitive user inputs.