Mangyu Kong

mangyukong2.jpg

mangyu0929@yonsei.ac.kr

50, Yonsei-ro, Seodaemun-gu, Seoul, Republic of Korea
Google Scholar | GitHub

I am Mangyu Kong, a Ph.D. student in Electrical and Electronic Engineering at Yonsei University and a member of CILAB. I received my B.S. degree in the same field at Yonsei University.

My research interests lie in computer vision and robotics, with a primary focus on 3D vision (3D Gaussian Splatting), SLAM, localization, and multi-robot systems.

Recently, I have been expanding my research toward Vision-Language-Action (VLA) models and autonomous navigation, aiming to bridge perception, reasoning, and decision-making in embodied systems.

My goal is to develop intelligent robotic systems capable of robust perception and adaptive behavior in complex real-world environments.

publications

  1. sgvideo.gif
    Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration
    Jaewon Lee, Mangyu Kong, and Euntai Kim
    In European Conference on Computer Vision (ECCV), 2026
  2. /assets/img/fig1.png
    Rethinking Pose Refinement in 3D Gaussian Splatting under Pose Prior and Geometric Uncertainty
    Mangyu Kong, Jaewon Lee, Seongwon Lee, and 1 more author
    In 2026 The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
  3. /assets/img/kong2025fast.gif
    Fast Global Localization on Neural Radiance Field
    Mangyu Kong, Jaewon Lee, Seongwon Lee, and 1 more author
    In 2025 IEEE International Conference on Robotics and Automation (ICRA), 2025
  4. geomgs.png
    GeomGS: LiDAR-Guided Geometry-Aware Gaussian Splatting for Robot Localization
    Jaewon Lee, Mangyu Kong, Minseong Park, and 1 more author
    arXiv preprint arXiv:2501.13417, 2025
  5. /assets/img/DGS-SLAM.gif
    DGS-SLAM: Gaussian Splatting SLAM in Dynamic Environments
    Mangyu Kong, Jaewon Lee, Seongwon Lee, and 1 more author
    arXiv preprint arXiv:2411.10722, 2024
  6. /assets/img/kong2023room.gif
    RoomNeRF: Representing Empty Room as Neural Radiance Fields for View Synthesis
    Mangyu Kong, Seongwon Lee, and Euntai Kim
    In 34th British Machine Vision Conference (BMVC), 2023