Dong-Uk Seo

Office: KAIST Urban Robotics Lab (URL)
E-mail: dongukseo@kaist.ac.kr

I’m currently interested in research to enable SLAM to be applied in social industries in a practical view. Specifically striving to research LiDAR-Visual-Inertial fusion SLAM, aiming for long-term autonomy that is robust to environmental changes. Also, the process collaborated with multi-agent and localization in the dense map representation are of my interests.

  • LiDAR-Visual-Inertial SLAM framework.
  • Multi-agent collaborated localization and map reconstruction.
  • Learning-based method for dense map reconstruction in visual SLAM.

Youtube / Github / CV


EDUCATION

  • KAIST, South Korea (Mar. 2023 ~ )
    • Ph.D. candidate in Department of Electrical Engineering
  • KAIST, South Korea (Mar. 2021 ~ Feb. 2023)
    • M.S. candidate in Department of Electrical Engineering
  • Yonsei University, South Korea (Mar. 2014 ~ Aug. 2020)
    • Bachelor’s Degree in Department of Electrical & Electronic Engineering


PUBLICATION

  • GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow [paper]
    Dong-Uk Seo, Jinwoo Jeon, Eungchang Mason Lee, and Hyun Myung The IEEE Robotics and Automation Letters (RA-L 2026), accepted

  • AIM-SLAM: Dense Monocular SLAM via Adaptive and Informative Multi-View Keyframe Prioritization with Foundation Model [paper]
    Jinwoo Jeon, Dong-Uk Seo, Eungchang Mason Lee, and Hyun Myung IEEE International Conference on Robotics and Automation (ICRA 2026)

  • PanoNetVLAD: Visual loop closure detection in continuous space represented with panoramic view using multiple cameras [paper]
    Sungjae Shin, Yeeun Kim, Byeongho Yu, Eungchang Mason Lee, Dong-Uk Seo, and Hyun Myung The 23rd International Conference on Control, Automation and Systems (ICCAS 2023)

  • Enhancing Robustness of Line Tracking Through Semi-Dense Epipolar Search in Line-based SLAM [paper]
    Dong-Uk Seo, HYUNGTAE LIM, Eungchang Mason Lee, Hyunjun Lim, and Hyun Myung IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023)

  • PaGO-LOAM: Robust Ground-Optimized LiDAR Odometry (Best paper finalist) [paper]
    Dong-Uk Seo*, Hyungtae Lim*, Seungjae Lee, and Hyun Myung Int’l Conf. on Ubiquitous Robots (UR 2022)

  • Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAM [paper]
    Jinwoo Jeon, Hyunjun Lim, Dong-Uk Seo, and Hyun Myung The IEEE Robotics and Automation Letters (RA-L 2022)

  • QR-SCAN: Traversable Region Scan for Quadruped Robot Exploration using Lightweight Precomputed Trajectory [paper]
    EungChang Mason Lee, DongUk Seo, JinWoo Jeon, and Hyun Myung The 21st International Conference on Control, Automation and Systems (ICCAS 2021)