Sangmin Kim

I am a Ph.D. student in Artificial Intelligence at Seoul National University, advised by Jaesik Park. Recently, I was a research intern at NAVER Cloud. I received my B.S. degree in Computer Science and Engineering from Chung-Ang University with honors of magna cum laude in 2024.

My research interests are in 3D computer vision and deep learning. Especially, I am interested in computer vision applications for post-production and visual contents.

Email / CV / Google Scholar / LinkedIn / Github / X

🎙️ News

June 18, 2026 A paper about scalable 4DGS has been accepted to ECCV 2026, Malmö.
May 6, 2026 I will be joining NAVER LABS Europe as a research intern in May 2027, Grenoble.
Apr 15, 2026 A paper about diffusion guided studio reconstruction has been accepted to SIGGRAPH 2026, Los Angeles.
Oct 20, 2025 I started a research internship at NAVER Cloud's Video Team.
Feb 27, 2025 A paper about TV show dynamic reconstruction has been accepted to CVPR 2025, Nashville.

Show All

🔬 Work Experience

	NAVER LABS Europe, Research Intern Grenoble, France (May 2027 - Nov 2027, Expected) Plan to work on 3D humans project. (Host: Fabien Baradel)
	NAVER Cloud, Research Intern Seongnam, Korea (Oct 2025 - Apr 2026) Worked on feed-forward 4D human-scene reconstruction. (Host: Dongyoon Wee)
	Deloitte, Consulting Intern Seoul, Korea (Nov 2021 - Feb 2022) Assisted consulting on revision of Shinhan Bank's ICT regulation.

📚 Publications

* indicates equal contribution. Representative papers are highlighted.

	TRiGS: Temporal Rigid-body Motion for Scalable 4D Gaussian Splatting Suwoong Yeom, Joonsik Nam, Seunggyu Choi, Lucas Yunkyu Lee, Sangmin Kim, Jaesik Park, Joonsoo Kim, Kugjin Yun, Kyeongbo Kong, Sukju Kang ECCV, 2026* project / paper
	FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles Lucas Yunkyu Lee, Soonho Kim, Youngwook Kim, Sangmin Kim, Jaesik Park arXiv, 2026 project / paper / code
	4D Human-Scene Reconstruction from Low-Overlap Captures Minhyuk Hwang, Sangmin Kim*, Seunguk Do, Daneul Kim, Jaesik Park SIGGRAPH, 2026* project
	Coherent Human-Scene Reconstruction from Multi-Person Multi-View Video in a Single Pass Sangmin Kim, Minhyuk Hwang, Geonho Cha, Dongyoon Wee, Jaesik Park arXiv, 2026 project / paper / code
	SEAL-pose: Enhancing 3D Human Pose Estimation via a Learned Loss for Structural Consistency Yeonsung Kim, Junggeun Do, Seunguk Do, Sangmin Kim, Jaesik Park, Jay-Yoon Lee arXiv, 2026 paper
	Optimized Minimal 4D Gaussian Splatting Minseo Lee, Byeonghyeon Lee, Lucas Yunkyu Lee, Eunsoo Lee, Sangmin Kim, Seunghyeon Song, Joo Chan Lee, Jong Hwan Ko, Jaesik Park, Eunbyung Park arXiv, 2025 project / paper / code
	ShowMak3r: Compositional TV Show Reconstruction Sangmin Kim, Seunguk Do, Daeun Lee, Jaesik Park CVPR, 2025 project / paper / extended paper / code

Website's source code is referenced from Jon Barron's.