I am a Senior student in electrical engineering at Kookmin University, advised by Prof. Seongwon Lee. And I've had a wonderful time pursuing research internship at CARIAD, advised by Dr. Xavier Timoneda. I'm always excited to collaborate—feel free to reach out!
My research lies at the intersection of 3D vision and robotics. I study how machines can build reliable neural and geometric representations of the physical world from visual observations. My current work focuses on multi-view 3D scene understanding, camera-only occupancy prediction, and Gaussian-based scene representations, with applications to autonomous driving and robotic perception.
In the long term, I want to build perception systems that allow autonomous and embodied agents to understand complex environments, reason about possible actions, and improve through interaction and experience.
RayOcc: Occlusion-Agnostic Ray Occupancy Estimation via Gaussian Mixture Intensity
Multi-surface Ray occupancy modeling with Gaussian mixture model.
High-Fidelity Vehicle Representation via 3D Gaussian Splatting
Reflective vehicle reconstruction with disentangled diffuse and specular appearance.
Junho Kim,
Sangho Byeon,
Jiseok Kim,
Seongwon Lee
Team Lead of We-Meet Project (Fall 2025)
Bosch Future Mobility Challenge 2024
Real-time autonomous driving perception and deployment on an embedded platform.
Minchan Jeong,
Junho Kim,
Dahyeon Ko,
Jaehyoung Park,
Donghwan Seo
Perception Engineer / ROS, Multi-View 3D object detection, V2X
3rd Prize, (top 3 out of 80 teams worldwide)
Experience
Kookmin University, Seoul, South Korea
2019.03 - Present
B.S. in Electrical Engineering Advisor: Prof. Seongwon Lee