이 성 오 Seongoh Lee

Combined MS/PhD Student

Links. [github] [3D Vision & Robotics Lab]

#707-1, Bldg 106, 50 UNIST-gil, Ulju, Ulsan, Republic of Korea, 44919

Short Bio.

I am a combined MS/PhD student affiliated to the Artificial Intelligence Graduate School (AIGS) at UNIST since March 2023. I obtained BS (2023) degrees in recognition of the fulfillment of the necessary requirements for the multi-disciplinary majors of Mechanical & Aerospace Engineering, School of Mechanical, Aerospace and Nuclear Engineering, and Physics, School of Natural Science at UNIST.

Research

My research is concentrated in the area of 3D machine vision, with an emphasis on real-time perception for robotic agents, vehicles, UAVs, and other similar systems. I specialize in the utilization of multi-camera and sensor systems, including neuromorphic sensors like Dynamic Vision Sensors (DVS) and Spike Cameras. Additionally, I explore the intricacies of 3D neural representations, such as Implicit Neural Representations (INR) and Neural Fields (NF), aiming to design efficient neural models that can effectively incorporate and respond to geometrical cues.

Project

Multi-Camera System on Autonomous Vehicle.

Toolbox of robust and accurate calibration method for multi-camera system on autonomous vehicle. This methods are based on the toolbox for autonomous vehicle, NVIDIA DriveWorks SDK.

Z-axis vibration estimation using stereo system

TBD.

Event-based denoising method with DDPM

TBD.

Publication

SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments

TBD