About

I am Hyunsoo Cha, a PhD student at Seoul National University, advised by Prof. Hanbyul Joo. I will be joining NVIDIA as a Research Scientist Intern starting June 2026. My research goal is to develop generative models that can understand and represent people in virtual worlds.

News

  • Jun 2026 Starting as a Research Scientist Intern at NVIDIA, Santa Clara.
  • Apr 2026 Vanast has been selected as a Highlight at CVPR 2026.
  • Feb 2026 Vanast has been accepted to CVPR 2026.
  • Jan 2026 Durian has been accepted to ICLR 2026.
  • Feb 2025 PERSE has been accepted to CVPR 2025.
  • Feb 2024 PEGASUS has been accepted to CVPR 2024.
  • Sep 2022 Joined SNU Visual Computing Lab as an MS/PhD student.
  • Jan 2022 Started as a Research Intern at SNU Visual Computing Lab.

Experience

Research Scientist Intern (Upcoming)
NVIDIA
Santa Clara, CA, USA · Jun 2026 -
Intern
DRAM Solution Team, Samsung Electronics
Hwaseong, Korea · Sep 2021 - Dec 2021

Publications

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
CVPR, 2026 Highlight

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision

Given a human image and one or more garment images, our method generates virtual try-on with human image animation conditioned on a pose video while preserving identity.

Animation Generative Models Virtual Try-On
Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer
ICLR, 2026

Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer

Hyunsoo Cha, Byungjun Kim, Hanbyul Joo

Given a portrait and one or more reference images specifying target attributes, Durian generates a portrait animation with attribute transfer in a single-stage pipeline.

Animation Appearance Editing Generative Models Virtual Try-On
PERSE: Personalized 3D Generative Avatars from A Single Portrait
CVPR, 2025

PERSE: Personalized 3D Generative Avatars from A Single Portrait

Hyunsoo Cha, Inhee Lee, Hanbyul Joo

A method for building an animatable personalized generative avatar from a reference portrait.

3D Avatar Appearance Editing Generative Models Virtual Try-On
PEGASUS: Personalized Generative 3D Avatars with Composable Attributes
CVPR, 2024

PEGASUS: Personalized Generative 3D Avatars with Composable Attributes

Hyunsoo Cha, Byungjun Kim, Hanbyul Joo

A method for constructing a personalized generative 3D face avatar from monocular videos.

3D Avatar Appearance Editing