Jaeseong Lee

I'm a Ph.D candidate at the Kim Jaechul Graduate School of AI, KAIST, advised by J. Choo. My research focuses on digital humans, particularly geometry processing and appearance matching of components such as hair, skin, and eyes, as well as facial deformation models. Earlier, I worked on 3DGS-based neural head avatars with rigging and relighting, and on 2D face swapping with generative models.

I have interned at Meta Reality Labs with C. Aliaga, Naver AI Lab with J. Kim, and Kakao Brain with H. Lee. I also collaborate with M. Buehler from ETH Zurich. I received my B.S. in Engineering from DGIST.

Email | Email2 | GitHub | Google Scholar | LinkedIn

Industry Experience

Meta Reality Labs, California, USA — Research Intern (Jul 2026 – Jan 2027, upcoming)
Host: T. Ma
Meta Reality Labs, Tokyo, Japan (Remote) — Contingent Research Scientist (Jan 2026 – Feb 2026)
Host: C. Aliaga
Meta Reality Labs, California, USA — Research Intern (Jun 2025 – Dec 2025)
Host: C. Aliaga
Naver AI Lab, Seongnam, Korea — Research Intern (Aug 2024 – Feb 2025)
Host: J. Kim
Kakao Brain, Seongnam, Korea — Research Intern (Jul 2022 – Sep 2022)
Host: H. Lee

Academic Experience

KAIST, Daejeon, Korea — Research Intern, DAVIAN Lab (Dec 2020 – Feb 2022)
Advisor: J. Choo
POSTECH, Pohang, Korea — Research Intern, Computer Graphics Lab (Jun 2020 – Aug 2020)
Advisor: S. Cho
DGIST, Daegu, Korea — Research Intern, Computer Vision Lab (Dec 2019 – Feb 2020)
Advisor: S. Im

Research

* denotes equal contribution, ^† denotes advisee

	GaussianTrimmer: Facial Hair Capture from Multi-view Images J. Lee, G. Nam, A. Jarabo, C. Aliaga Working title, 2026
	TexAvatars: Hybrid Texel-3D Representations for Stable Rigging of Photorealistic Gaussian Head Avatars J. Lee, J. Ahn^†, T. Kang, J. Choo International Conference on 3D Vision (3DV), 2026 paper \| project page \| cite
	SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars J. Lee, T. Kang, M. Bühler, M. Kim, S. Hwang, J. Hyung, H. Jang, J. Choo International Conference on Learning Representations (ICLR), 2025 paper \| project page \| cite
	Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting J. Hyung, S. Hong, S. Hwang, J. Lee, J. Choo, J. Kim Conference on Neural Information Processing Systems (NeurIPS), 2024 paper \| project page \| cite
	SelfSwapper: A Simple yet Robust Face Swapping Model against Attribute Leakage J. Lee, J. Hyung, S. Jung, J. Choo European Conference on Computer Vision (ECCV), 2024 paper \| project page \| cite
	Expression Domain Translation Network for Cross-domain Head Reenactment T. Kang^†, J. Oh, J. Lee, S. Park, J. 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 K. Kim, S. Park, J. Lee, S. Chung, J. Lee, J. Choo European Conference on Computer Vision (ECCV)*, 2022 paper \| code \| cite

Mentored Students

T. Kang (2023–2025): Ph.D student at KAIST
EDTN (ICASSP 2024)
J. Ahn (2024–2025): M.S. student at KAIST
TexAvatars (3DV 2026)

Projects

	PixelHuman: Animatable Neural Radiance Fields from Few Images G. Shim, J. Lee, J. Hyung, J. Choo arXiv preprint, 2023 paper
	RobustSwap: A Simple yet Robust Face Swapping Model against Attribute Leakage J. Lee, T. Kim, S. Park, Y. Lee, J. Choo arXiv preprint, 2023 paper \| project page

Education

Ph.D. in Artificial Intelligence, KAIST, 2025 – Present
Advisor: J. Choo
M.S. in Artificial Intelligence, KAIST, 2022 – 2025
Advisor: J. Choo
B.S. in Engineering, DGIST, 2018 – 2022
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