Seoha Kim

PhD Student

seoha.kim@student.unimelb.edu.au

About

I am an incoming PhD student at the University of Melbourne, co-supervised by Prof. Taehyun Rhee and Prof. Kris Ehinger. My research aims to enable AI to perceive and understand dynamic 3D environments for embodied AI. My interests include dynamic 3D reconstruction and understanding, vision-language models, multimodal large language models, and 3D scene graphs.

Previously, I received my Master's degree from Yonsei University under the supervision of Prof. Youngjung Uh, where I focused on dynamic 3D reconstruction, especially dynamic Gaussian Splatting and NeRF.

Publications

indicates equal contribution.

Efficient 4D Scaffold Gaussian Splatting with Dynamic‑Aware Anchor Growing

Woong Oh Cho, In Cho, Seoha Kim, Jeongmin Bae, Youngjung Uh, Seon Joo Kim

AAAI 2026

Compensating Spatiotemporally Inconsistent Observations for Online Dynamic 3D Gaussian Splatting

Youngsik Yun, Jeongmin Bae, Hyunseung Son, Seoha Kim, Hahyun Lee, Gun Bang, Youngjung Uh

SIGGRAPH 2025

Rethinking Open-Vocabulary Segmentation of Radiance Fields in 3D Space

Hyunjee Lee, Youngsik Yun, Jeongmin Bae, Seoha Kim, Youngjung Uh

AAAI 2025

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

Jeongmin Bae, Seoha Kim, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh

ECCV 2024

Optimizing Dynamic NeRF and 3DGS with No Video Synchronization

Seoha Kim, Jeongmin Bae, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh

ECCV 2024 Wild3D Workshop

Sync-NeRF: Generalizing Dynamic NeRFs to Unsynchronized Videos

Seoha Kim, Jeongmin Bae, Youngsik Yun, Hahyun Lee, Gun Bang, Youngjung Uh

AAAI 2024

Vitae

  • University of Melbourne 2026.2 -
    PhD Student
    Computing and Information Systems
  • ETRI 2025.02 - 2025.11
    Post-Master's Research Fellow
    Generalizable Dynamic Scene Reconstruction
  • Meta Reality Labs & Microsoft Zurich 2024.9 -
    Research Collaboration (External)
    Generalizable Dynamic Scene Reconstruction
  • ETRI 2023.1 - 2024.6
    Research Collaboration
    Dynamic Scene Reconstruction
  • LG Display 2022.2 ‑ 2022.12
    Research Collaboration
    Knowledge Distillation
  • Yonsei University 2022.3 – 2024.8
    Master
    Artificial Intelligence
  • Plask 2021.3 – 2021.8
    AI Engineer
    3D Pose Estimation
  • Hyundai Mobis 2019.9 – 2020.2
    Data Scientist Intern
    Structured Data Analysis
  • Yonsei University 2015.3 - 2021.2
    Bachelor
    Business Administration