Sihun Cha
[ɕihʌn tʃɑ]

I am a Ph.D student at Visual Media Lab, KAIST, advised by Prof. Junyong Noh. I studied Fine Arts as a Bachelor at Korea National University of Arts.

‘How to create and control 3D content intuitively?’ is my overall question. My current research interest focuses on generating and editing facial animation.


Research

Mesh Agnostic Audio-Driven 3D Facial Animation

Mesh Agnostic Audio-Driven 3D Facial Animation

* Kwanggyoon Seo, * Sihun Cha, Hyeonho Na, Inyup Lee, Junyong Noh (*equal contribution)
Under review

An end-to-end method for animating a 3D face mesh with arbitrary shape and triangulation from a given speech audio.

SALAD: Skeleton-Aware Latent Diffusion for Text-driven Motion Generation and Editing

SALAD: Skeleton-Aware Latent Diffusion for Text-driven Motion Generation and Editing

CVPR 2025

Skeleton-Aware LAtent Diffusion (SALAD) model that explicitly captures the intricate inter-relationships between joints, frames, and words.

Neural Face Skinning for Mesh-agnostic Facial Expression Cloning

Neural Face Skinning for Mesh-agnostic Facial Expression Cloning

Eurographics 2025, Computer Graphics Forum (CGF)

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

Deep Learning-Based Facial Retargeting Using Local Patches

Deep Learning-Based Facial Retargeting Using Local Patches

* Yeonsoo Choi, * Inyup Lee, Sihun Cha, Seonghyeon Kim, Sunjin Jung, Junyong Noh (*equal contribution)
Computer Graphics Forum (CGF)

Retargeting facial expression from a source human performance video to a target stylized 3D character using local patches.

NeRFFaceSpeech: One-shot Audio-diven 3D Talking Head Synthesis via Generative Prior

NeRFFaceSpeech: One-shot Audio-diven 3D Talking Head Synthesis via Generative Prior

CVPR Workshop 2024

One-Shot Audio-driven 3D talking head generation with enhanced 3D consistency using NeRF and generative knowledge from single image input.

Generating Texture for 3D Human Avatar from a Single Image using Sampling and Refinement Networks

Generating Texture for 3D Human Avatar from a Single Image using Sampling and Refinement Networks

Eurographics 2023, Computer Graphics Forum (CGF)

Generating 3D human texture from a single image using sampling and refinement process by utilizing geometry information.

Reference Based Sketch Extraction via Attention Mechanism

Reference Based Sketch Extraction via Attention Mechanism

SIGGRAPH Asia 2022, ACM Transactions on Graphics (TOG)

Extracting a sketch from an image in the style of a given reference sketch while preserving the visual content of the image.

Generating 3D Human Texture from a Single Image with Sampling and Refinement

Generating 3D Human Texture from a Single Image with Sampling and Refinement

SIGGRAPH 2022 Posters

A method for generating 3D human texture from a single image based on SMPL model, using sampling and refinement process.

“Anyway,”: Two-player Defense Game via Voice Conversation

“Anyway,”: Two-player Defense Game via Voice Conversation

* Minki Hong, * YoungJun Choi, * Sihun Cha (*equal contribution)
CHI Play 2021

A two-player conversational defense game that uses voice conversation as an input.