HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Mon, 08 Dec 2025 04:58:44 GMT access-control-allow-origin: * etag: W/"69365b04-350e" expires: Sun, 28 Dec 2025 13:34:28 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 6DAF:292AC1:7A3EF1:890EAD:69512F8C accept-ranges: bytes age: 0 date: Sun, 28 Dec 2025 13:24:28 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210039-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766928269.724825,VS0,VE208 vary: Accept-Encoding x-fastly-request-id: e41ac4c3843b317d72eaa532d448c86ec5804bc9 content-length: 2471

Hyunsoo Cha

I am Hyunsoo Cha, a PhD student at Seoul National University, advised by Prof. Hanbyul Joo.

CV Scholar GitHub X(Twitter) LinkedIn

Publications

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

Hyunsoo Cha, Byungjun Kim, Hanbyul Joo

ArXiv, 2025

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.

Project Page PDF arXiv Code

PERSE: Personalized 3D Generative Avatars from A Single Portrait

Hyunsoo Cha, Inhee Lee, Hanbyul Joo

CVPR, 2025

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

Project Page PDF arXiv Code

PEGASUS: Personalized Generative 3D Avatars with Composable Attributes

Hyunsoo Cha, Byungjun Kim, Hanbyul Joo

CVPR, 2024

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

Project Page PDF arXiv Code