Seoha Kim

About

I am currently master student in Artificial Intellifence at Yonsei University, advised by Prof. Youngjung Uh.
My research interests are 3D/4D reconstruction, especially with Neural Radiance Fields and Gaussian Splatting.

Publications

^‡ indicates equal contribution.

All

Per-Gaussian Embedding based Deformation for Deformable 3D Gaussian Splatting

_{Jeongmin Bae^‡, Seoha Kim^‡, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh}

_{Sumitted to ECCV 2024}

Project Paper Code

Sync-NeRF: Generalizing Dynamic NeRFs to Unsynchronized Videos

_{Seoha Kim^‡, Jeongmin Bae^‡, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh}

_{AAAI 2024}

Project Paper Code Data

Vitae

ETRI 2023.01 - Present

Academic-Research Cooperation
Dynamic Scene Reconstruction Research
LG Display 2022.2 ‑ 2022.12

Academic-Industrial Cooperation
Knowledge Distillation Research
Yonsei University 2022 – 2024

M.S. Student
Artificial Intelligence
Plask 2021.3 – 2021.8

AI Engineer
3D Pose Estimation Research
Hyundai Mobis 2019.9 – 2020.2

Data Scientist, Intern
Internship in Data Science Team
Yonsei University 2015 - 2021

B.A. Student
Business Administration

Korean Patents

10-2024-0043684, Method and apparatus for Dynamic Gaussian Splatting using embedding-based deformation
10-2023-0105173, Apparatus for representing dynamic neural radiance fields from unsynchronized videos
10-2020-0022362, Apparatus of diagnosing noise quality of motor