Jungwan Woo

Jungwan Woo

Ph.D. student

About me

I’m Jungwan Woo, an integrated M.S.–Ph.D. student in Electrical Engineering and Computer Science at DGIST. My research focuses on 3D perception and spatial intelligence for real-world, including LiDAR-based scene understanding, domain generalization, and spatio-temporal motion forecasting for autonomous driving. I am particularly interested in building robust 3D vision models that generalize across environments and sensor configurations, and in applying them to embodied AI and robotics in everyday scenarios. I am conducting my research under my advisor, Prof. Sunghoon Im.

Publications

Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation

Jaeyeul Kim, Jungwan Woo, Ukcheol Shin, Jean Oh, Sunghoon Im
IEEE Robotics and Automation Letters (RA-L), 2025 Winner of the Argoverse 2 LiDAR Scene Flow Challenge at CVPR 2024 WAD
Paper

Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains

Jaeyeul Kim*, Jungwan Woo*, Jeonghoon Kim, Sunghoon Im
European Conference on Computer Vision (ECCV), 2024.
Paper

Density-aware Domain Generalization for LiDAR Semantic Segmentation

Jaeyeul Kim*, Jungwan Woo*, Ukcheol Shin, Jean Oh, Sunghoon Im
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024.
Paper

Motion Forecasting via Coordinate Transformations and Object Trajectory Modifications

Jungwan Woo*, Jaeyeul Kim*, Sunghoon Im
CVPR Workshop on Autonomous Driving (CVPRw), 2023. (2nd place in the challenge)
Paper

LiDAR 3D Object Detection via Self-Training and Knowledge Distillation

Jungwan Woo*, Jaeyeul Kim*, Sunghoon Im
ECCV Workshop on 3D Perception for Autonomous Driving (ECCVw), 2022. (3rd place in the challenge)
Paper

RVMOS: Range-View Moving Object Segmentation Leveraged by Semantic and Motion Features

Jaeyeul Kim*, Jungwan Woo*, Sunghoon Im
IEEE Robotics and Automation Letters (RA-L / IROS), 2022.
Paper

Awards and Achievements

  • Winner, Argoverse LiDAR Scene Flow Challenge at CVPR WAD, 2024.
  • DGIST Post-Graduate Research Abroad Award (DPRAA), 2024
    • Visiting Researcher at Carnegie Mellon University
  • Honorable Mention, Argoverse Forecasting Challenge at CVPR WAD, 2023.
  • Best Robot Vision Paper Award, Asian Federation of Computer Vision (AFCV), KRoC 2023.
  • 1st place, Autonomous Driving A.I. Challenge (organized by MOLIT), 2023.
  • 2nd place, Autonomous Driving A.I. Challenge (organized by MOLIT), 2022.
  • 3rd place, ECCV Workshop on 3D Perception for Autonomous Driving, 2022.

Projects

  • Dabeeo — Advanced Deep Learning-Based Geographic Data Construction System (2020–2021)
    • Developed precise 3D urban reconstruction pipelines from multi-view aerial imagery.
  • P-CoE — Collaborative AI-based Remote Autonomous Driving Cloud Mobility Service System (2021–2022)
    • Built camera–LiDAR fused driving datasets by performing sensor calibration on a real vehicle and collecting annotated road-driving data.
    • Developed real-time perception models for depth and relative speed estimation of surrounding vehicles, as well as traffic-light detection and signal recognition.
  • National Research Foundation of Korea — Outstanding Young Researcher Program (2023)
    • Robust multi-camera learning for multi-task visual perception under environmental variations.
  • Huvitz — Dental Intraoral Scanning Software Development (2023–2024)
    • Enhanced structured-light 3D dental scanning accuracy with loop closure detection and pose graph optimization.
  • Ministry of Science and ICT — Advanced AX Research Support Platform Development Project (2025)
    • Implemented a cloud-based robot navigation pipeline, enabling simulation-based training and validation on the cloud and deploying navigation models to real-world robots.

Education

Integrated M.S.–Ph.D. in Electrical Engineering and Computer Science (EECS), DGIST, Korea
February 2019 – Present (Advisor: Prof. Sunghoon Im)

Visiting Researcher, Carnegie Mellon University (CMU), Pittsburgh, PA, USA
January 2024 – May 2024 (Robot Intelligence Group, Robotics Institute)

Summer Session (8 credits), Stanford University, CA, USA
June 2015 – July 2015 (Supported by DGIST Freshmen Global Leadership Program, FGLP)

B.S. in Convergence Science, DGIST, Korea
March 2015 – February 2019

Skills

  • Programming Languages: Python, C++
  • Deep Learning Frameworks: PyTorch, TensorFlow, JAX
  • 3D Perception from Point Clouds and Images
  • 3D Reconstruction and Structured-light Scanning
  • Scene Flow Estimation and 3D Semantic Segmentation
  • Multimodal Sensor Fusion (Camera–LiDAR)
  • ROS/ROS2 and LeRobot for robot navigation and control