Junmyeong Lee

junmyeong_profile.jpeg

I am an Ph.D. student at the Graduate School of Artificial Intelligence at POSTECH and a member of the Computer Vision Lab, advised by Prof.Minsu Cho.

My research focuses on 3D vision and representation learning, aiming to reconstruct expressive and geometrically consistent 3D/4D scene representations from visual observations. I am particularly interested in dynamic scene reconstruction, novel view synthesis, and integrating semantic cues to enhance the geometric and temporal consistency of learned representations.

Education

Mar, 2024 - Present Pohang University of Science and Technology (POSTECH), Pohang, South Korea
M.S. student in Graduate School of Artificial Intelligence
Advisor: Prof. Minsu Cho
Mar, 2018 - Feb, 2024 Gwangju Institute of Science and Technology (GIST), Gwangju, South Korea
B.S. in Electrical Engineering and Computer Sciences
TGPA : 4.13/4.5 (Magna Cum Laude)

Publications

  1. MoGaF: Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping
    Junmyeong Lee*, Hoseung Choi*, and Minsu Cho(* : equal contribution)
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
  2. RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos
    Yoonwoo Jeong*, Junmyeong Lee*, Hoseung Choi*, et al.(* : equal contribution)
    arXiv preprint, 2024
  3. CanonicalFusion: Generating Drivable 3D Human Avatars from Multiple Images
    Jisu Shin, Junmyeong Lee, Seongmin Lee, et al.
    European Conference on Computer Vision (ECCV), 2024

Experience

Aug, 2021 - Dec, 2022 VoyagerX, Seoul, Korea
Team vFlat - ML engineer
  • On-device inference optimization using TFLite and ONNX.
  • Build Millon-scale data pipeline for training and evaluation.
Jan, 2021 - May, 2021 Search CIC, Naver Corp., Seoul, Korea
Research Intern
  • Research Topic : Large-scale Vector Retrieval Optimization