Beyond Idealized Assumptions: Advancing 3D Scene Understanding for Real-World Applications
Before joining KT, I earned my M.S. from POSTECH, where I conducted research in the Computer Graphics Lab under the supervision of Prof. Sunghyun Cho.
My research interests span a broad range of topics in computer vision, with a particular emphasis on approaches that are applicable to real-world scenarios. I am currently focused on developing robust 3D scene representations and rendering techniques that remain effective even under challenging, non-ideal conditions.
The overarching goal of my research is to move beyond idealized assumptions, embracing the complexity of real-world scenarios. If you're interested in my research, feel free to reach out!
News
Publications
Optical Flow-based Shakiness Detection in Dash-cams for Hit-and-Run Accident Analysis
Haeyun Choi, Sunghyun Cho
Workshop on Image Processing and Image Understanding (IPIU 2024)
AutoCycle-VC: Towards Bottleneck-Independent Zero-Shot Cross-Lingual Voice Conversion
Haeyun Choi, Jio Gim, Yuho Lee, Youngin Kim, Youngjoo Suh
arXiv Preprint (2023)
Projects
Real-time Danger Alert for Convenience Stores by Motion and Voice Recognition
Excellence Prize at POSCO Youth Academy AI Competition (2022)
Wear Your Mask On: Real-time Mask Detection & Warning System
Grand Prize at AI for Health & SDGs Competition (2021)
Extracurricular Activities
Team-Mate Mentorship Program (K-Digital Training)
Aug 2024 – Present
- Selected as 1st cohort mentor in a national career development program
- Peer mentorship program, supporting junior trainees in career navigation
- Engaged in job camps and social contribution programs
Military Service (Republic of Korea Air Force)
Aug 2016 – Aug 2018
- Sergeant as Operations
- Maintained 24/7 emergency standby status for mission deployment
- Managed mission planning and scheduling for search and rescue operations