Sihun Cha

Ph.D. student

Sihun Cha

homepage

art work

chacorp@kaist.ac.kr

Education

Korea Advanced Institute of Science and Technology
Ph.D. student in Computer Science, advised by Junyong Noh.
2022 - Present
Korea Advanced Institute of Science and Technology
M.S. in Computer Science, advised by Junyong Noh.
2020 - 2022
Korea National University of Arts
B.F.A. in Fine Arts
2013 - 2020

Experience

Visual Media Lab, KAIST
Research Assistant.
Worked on topics of texture generation, 3D facial animation.
Jan 2021 - Present
DaeJeon, South Korea
Mandatory Military Service
ROK Army sergeant, honorable discharge
June 2015 - Mar 2017
Uljin, South Korea
Flawless AI
Research Scientist Intern
Audio to Mouth Synthesis.
Sep 2024 - Dec 2024
Santa Monica, US

Publications

Mesh Agnostic Audio-Driven 3D Facial Animation
K. Seo, S. Cha, H. Na, I. Lee, J. Noh
An end-to-end method for animating a 3D face mesh with arbitrary shape and triangulation from a given speech audio.
Under review
Neural Face Skinning for Mesh-agnostic Facial Expression Cloning
S. Cha, S. Yoon, K. Seo, J. Noh
A method that enables direct retargeting between two facial meshes with different shapes and mesh structures.
Under review
Deep Learning-Based Facial Retargeting Using Local Patches
Y. Choi, I. Lee, S. Cha, S. Kim, S. Jung, J. Noh
Retargeting facial expression from a source human performance video to a target stylized 3D character using local patches.
Computer Graphics Forum (CGF)
NeRFFaceSpeech: One-shot Audio-diven 3D Talking Head Synthesis via Generative Prior
G. Kim, K. Seo, S. Cha, J. Noh
One-Shot Audio-driven 3D talking head generation with enhanced 3D consistency using NeRF and generative knowledge from single image input.
CVPRW 2024
LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example
S. Yoon, K. Yun, K. Seo, S. Cha, J. Yoo, J. Noh
Creating an animatable stylized 3D face mesh with one example pair.
CVPR 2024
Generating Texture for 3D Human Avatar from a Single Image using Sampling and Refinement Networks
S. Cha, K. Seo, A. Ashtari, J. Noh
Generating 3D human texture from a single image using sampling and refinement process by utilizing geometry information.
Eurographics 2023
Reference Based Sketch Extraction via Attention Mechanism
A. Ashtari, C. Seo, C. Kang, S. Cha, J. Noh
Extracting a sketch from an image in the style of a given reference sketch while preserving the visual content of the image.
SIGGRAPH Asia 2022
Generating 3D Human Texture from a Single Image with Sampling and Refinement
S. Cha, K. Seo, A. Ashtari, J. Noh
A method for generating 3D human texture from a single image based on SMPL model, using sampling and refinement process.
SIGGRAPH 2022 Posters
“Anyway,”: Two-player Defense Game via Voice Conversation
M. Hong, Y. Choi, S. Cha
A two-player conversational defense game that uses voice conversation as an input.
CHI Play 2021

Projects

Development of Universal Fashion Creation Platform Technology for Avatar Personality Expression (KOCCA)
Project Manager
Jun. 2023 ~ Ongoing
Development of Core SW Technology for Realistic 3D Facial Animation Generation (Metaverse Entertainment)
Software Developer
Aug. 2022 ~ Jan. 2024
3D Cinemagraph for AR Contents Creation (IITP)
Software Developer
Jun. 2021 ~ Dec. 2022
Development of self-evolving AI Creation Platform (KOCCA)
Software Developer
Jun. 2021 ~ Dec. 2022

Exhibition

Peer to Peer
단체전 (group exhibition)
온수공간, Seoul
2022
Peer to Peer
단체전 (group exhibition)
토포하우스 (Topohaus), Seoul
2021
영구 보존을 위한 휘핑에 샷추가 (레귤러)
개인전 (solo exhibition)
쇼앤텔 (show and tell), Seoul
2020
Mass 2020
단체전 (group exhibition)
Czong Institute for Contemporary Art (CICA) Museum, Gimpo-si
2020
ModelHouse: HM05
단체전 (group exhibition)
LOUNGE 32. Seoul
2020
전시후도록 Exhibition Publication
단체전 (group exhibition)
WESS, Seoul
2020
드로잉을 위한 드로잉
단체전 (group exhibition)
Korea National University of Arts Theory Gallery, Seoul
2019
SHOWCASE 2019: Playing the future
단체전 (group exhibition)
성북예술창작터 (Seoungbuk Young Art Space), Seoul
2019