Jaeseong Lee

I am a Ph.D candidate supervised by Jaegul Choo, at Kim Jaechul Graduate School of AI, KAIST. My research interest lies in reconstructing photo-realistic human heads with controllability. Particularly, my research topics include neural head avatar synthesis with rigging or relighting. I have worked on 2D face swapping with generative models, before.

Currently, I am a research intern at Meta Reality Labs with Carlos Aliaga. I collaborate with Marcel Buehler from ETH Zurich. I was a research intern at Naver AI Lab with Jin-Hwa Kim and Kakao Brain with Hyunjoon Lee. I completed my Ph.D coursework in Computer Vision and Artificial Intelligence at KAIST, and a Bachelors in Engineering at DGIST.

Email | Email2 | GitHub | Google Scholar | LinkedIn

News

06/2025 Started a research internship at Meta Reality Labs, California.
01/2025 SurFhead is accepted to ICLR 2025.
09/2024 erankGS is accepted to NeurIPS 2024.
07/2024 SelfSwapper is accepted to ECCV 2024.
08/2024 Started a research internship at Naver AI Lab.
01/2024 EDTN is accepted to ICASSP 2024.
08/2022 AnimeCeleb is accepted to ECCV 2022.
07/2022 Started a research internship at Kakao Brain.

Research

* denotes equal contribution, ^† denotes advisee

	TexAvatars: Hybrid Texel-3D Representations for Stable Rigging of Photorealistic Gaussian Head Avatars Jaeseong Lee, Junyeong Ahn^†, Taewoong Kang, Jaegul Choo International Conference on 3D Vision (3DV), 2026 paper \| project page \| cite
	SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars Jaeseong Lee, Taewoong Kang, Marcel C. Bühler, Min-Jung Kim, Sungwon Hwang, Junha Hyung, Hyojin Jang, Jaegul Choo International Conference on Learning Representations (ICLR), 2025 paper \| project page \| cite
	Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting Junha Hyung, Susung Hong, Sungwon Hwang, Jaeseong Lee, Jaegul Choo, Jin-Hwa Kim Conference on Neural Information Processing Systems (NeurIPS), 2024 paper \| project page \| cite
	SelfSwapper: A Simple yet Robust Face Swapping Model against Attribute Leakage Jaeseong Lee, Junha Hyung, Sohyun Jung, Jaegul Choo European Conference on Computer Vision (ECCV), 2024 paper \| project page \| cite
	Expression Domain Translation Network for Cross-domain Head Reenactment Taewoong Kang^†, Jeongsik Oh, Jaeseong Lee, Sunghyun Park, Jaegul Choo IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024 paper \| project page \| cite
	AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment Kangyeol Kim, Sunghyun Park, Jaeseong Lee, Sunghyo Chung, Junsoo Lee, Jaegul Choo European Conference on Computer Vision (ECCV)*, 2022 paper \| code \| cite

Mentored Students

Taewoong Kang (2023–Present): Ph.D student at KAIST
EDTN (ICASSP 2024)
Junyeong Ahn (2024–Present): M.S. student at KAIST
TexAvatars (3DV 2026)

Projects

	PixelHuman: Animatable Neural Radiance Fields from Few Images Gyumin Shim, Jaeseong Lee, Junha Hyung, Jaegul Choo arXiv preprint, 2023 paper
	RobustSwap: A Simple yet Robust Face Swapping Model against Attribute Leakage Jaeseong Lee, Taewoo Kim, Sunghyun Park, Younggun Lee, Jaegul Choo arXiv preprint, 2023 paper \| project page

Experience

Meta Reality Labs, California, USA — Research Intern (Jun 2025 – Present)
Host: Carlos Aliaga
Naver AI Lab, Seongnam, Korea — Research Intern (Aug 2024 – Feb 2025)
Host: Jin-Hwa Kim
Kakao Brain, Seongnam, Korea — Research Intern (Jul 2022 – Sep 2022)
Host: Hyunjoon Lee
KAIST DAVIAN Lab, Daejeon, Korea — Research Intern (Dec 2020 – Feb 2022)
Advisor: Jaegul Choo
POSTECH, Pohang, Korea — Research Intern, Computer Graphics Lab (Jun 2020 – Aug 2020)
DGIST, Daegu, Korea — Research Intern, Computer Vision Lab (Dec 2019 – Feb 2020)

Education

Ph.D. in Artificial Intelligence, KAIST, 2022 – Present
Advisor: Jaegul Choo
B.S. in Engineering, DGIST, 2021
Summer Exchange, UC Berkeley, 2018

Academic Activities

Conference Reviewer: 3DV 2026, ICLR 2025, ICCV 2023/2025, CVPR 2022/2023/2024, ECCV 2022/2024, ACCV 2024

Talks

2023 SKT Computer Vision Research Seminar: "Image Animation with Deep Learning"
2022 NAVER & KAIA Autumn Joint Academic Conference: "Cross-domain Neural Talking Head Synthesis"

template adapted from this awesome website