Skip to content
View seoha-kim's full-sized avatar
📚
📚

Block or report seoha-kim

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
seoha-kim/README.md

Seoha Kim

I am a Graduate Researcher at the University of Melbourne, co-supervised by Prof. Taehyun Rhee and Prof. Kris Ehinger.
My research aims to enable embodied AI to perceive and reason about dynamic 3D environments.
My interests include 4D human--object interaction understanding, functional 3D scene understanding, world models, and vision--language--action (VLA) models.

🎓 Education

  • Graduate Researcher in Computing and Information Systems, University of Melbourne 2026.2 ~ Present
  • Master in Artificial Intelligence, Yonsei University 2022.3 ~ 2024.8
  • Bachelor in Business Administration and Cognitive Science (Double Major), Yonsei University 2015.3 ~ 2021.2

💭 Research Collaboration

  • Meta Reality Labs/Microsoft Zurich 2024.9 ~
  • Electronics and Telecommunications Research Institute (ETRI) 2023.1 ~ 2024.6
  • LG Display 2022.2 ~ 2022.12

📑 Selected Papers

  • Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos Under Review
  • Per-Gaussian Embedding based Deformation for Deformable 3D Gaussian Splatting ECCV 2024
  • Sync-NeRF: Generalizing Dynamic NeRFs to Unsynchronized Videos AAAI 2024

Pinned Loading

  1. E-D3DGS E-D3DGS Public

    Forked from JeongminB/E-D3DGS

    [ECCV 2024] Official repository for "Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting"

    Python 2

  2. Sync-4DRF Sync-4DRF Public

    [ECCVW 2024] Official repository for "Optimizing Dynamic NeRF and 3DGS with No Video Synchronization"

    5

  3. Sync-NeRF Sync-NeRF Public

    [AAAI 2024] Official repository for "Sync-NeRF: Generalizing Dynamic NeRFs to Unsynchronized Videos"

    Jupyter Notebook 60 4

  4. 4D-Scaffold-GS 4D-Scaffold-GS Public

    Forked from raikuma/4D-Scaffold-GS

    [AAAI 2026] 4D Scaffold Gaussian Splatting with Dynamic-Aware Anchor Growing for Efficient and High-Fidelity Dynamic Scene Reconstruction

    Python

  5. OR2 OR2 Public

    Forked from bbangsik13/OR2

    [SIGGRAPH 2025] Official implementation for "Compensating Spatiotemporally Inconsistent Observations for Online Dynamic 3D Gaussian Splatting"

    Python

  6. Open3DRF Open3DRF Public

    Forked from hyunji12/Open3DRF

    [AAAI 2025] Official repository for "Rethinking Open-Vocabulary Segmentation of Radiance Fields in 3D Space"