PROFESSIONAL SERVICE
IEEE Access
Peer Reviewer · Nov. 2025 – Present
ABOUT
A focus on spatial understanding.
I am Byeong Gwon Lee, a 3D Computer Vision Researcher at KETI. My work connects camera tracking, dense depth estimation, and 3D reconstruction.
RESEARCH INTERESTS
Learned priors.
Geometric foundations.
I work on online mapping and offline reconstruction, with interests in reliable depth estimation, adaptive view selection, and geometry completion.
EXPERIENCE
Research in practice.
-
Sep. 2026 – Present
KETICurrent
Researcher
-
Jul. 2026 – Jul. 2026
StradVision
Researcher
-
May 2026 – Jul. 2026
MotifDrive
Researcher
-
Sep. 2022 – Feb. 2024
RTM AI Image
2D Computer Vision Researcher
Manufacturing defect detection, image segmentation, model optimization, and few-shot auto labeling. Progressed from research intern to data scientist.
EDUCATION
A foundation in vision.
-
Mar. 2024 – Feb. 2026
Dongguk University
M.S. in Computer Science and Artificial Intelligence
Advisor: Prof. Soohwan Song
Thesis: Online 3D Gaussian Splatting Modeling with Novel View Selection
-
Mar. 2020 – Feb. 2023
Hanyang University ERICA
B.S. in Software Engineering
ACADEMIC COMMUNITY
Service & intellectual property.
PATENT APPLICATIONS
Online multi-view stereo for 3D modeling
온라인 다시점 스테레오를 이용한 3차원 모델링 시스템 및 방법
Korean patent application · Principal inventor
System and Method for 3D Modeling Using Online Multi-view Stereo
PCT international patent application · Principal inventor
TOOLS & METHODS
Built around the research.
- Geometry & reconstruction
- SLAM, Multi-View Stereo, Gaussian Splatting, bundle adjustment, COLMAP, OpenMVS
- Learning & implementation
- Python, PyTorch, C/C++, CUDA
- Computer vision
- Depth estimation, object detection, image segmentation, few-shot learning
- Research infrastructure
- Linux, Git, Docker, Kubernetes
LET’S CONNECT
Better geometry.
New perspectives.
For research discussions and collaborations in 3D vision.