Junsu Kim (김준수)

Ph.D Student @ 3D Vision and Robotics Lab, UNIST

id_photo.jpg

I am a Ph.D student in the 3D Vision & Robotics Lab, Department of Artificial Intelligence at UNIST, advised by Kyungdon Joo. Previously, I worked as an intern at 42dot Inc. and the BIG (Bot Intelligence Group) of the Robotics Institute at CMU, advised by Jean Oh. I received B.S. from the Department of Automobile and IT Convergence at Kookmin University, advised by Sanghun Lee.

My research interests lie in 3D Vision and Robotics, particularly in solving real-world problems related to robot vision.

Description Description Description Description

News

Feb 02, 2026 Our paper “Prior-Constrained Explorative Guidance for Generalization in Diffusion Motion Planning” has been accepted to ICRA 2026!
Jul 02, 2025 Our paper “VPOcc: Exploiting Vanishing Point for 3D Semantic Occupancy Prediction” has finally been accepted to IROS 2025!
May 22, 2025 I’ll be presenting my poster at the Foundation Models for V2X-based Cooperative Autonomous Driving workshop @ CVPR 2025. Come by and say hi!
Feb 20, 2025 I received the Silver Prize🏆 at the 31st Samsung Humantech Paper Award ($7000)!

Publications

  1. Robotics
    preview_prior.gif
    Prior-Constrained Explorative Guidance for Generalization in Diffusion Motion Planning
    Sunhwi Kim, Junsu Kim, Seungjae Baek, Jaechan Shin, Jungeun Lee, Seongjae Lee, Kyungdon Joo, and Jeong hwan Jeon
    IEEE International Conference on Robotics & Automation (ICRA), 2026
  2. Vision
    preview_vpocc.gif
    VPOcc: Exploiting Vanishing Point for 3D Semantic Occupancy Prediction
    Junsu Kim, Junhee Lee, Ukcheol Shin, Jean Oh, and Kyungdon Joo
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025
    Short version at Foundation Models for V2X-based Cooperative Autonomous Driving @ CVPR 2025 Workshop
    🏆Silver Prize at the Samsung Humantech Paper Award

Projects

  1. Vision
    tl3d.gif
    MT3D: A 3D Missing Tooth Detection Framework and Dataset
    Junsu Kim
    On-going, 2024
  2. Vision
    monofish.gif
    MonoFish: Depth-aware Monocular Fisheye 3D Object Detection
    Junsu Kim
    On-going, 2024
  3. Robotics
    bimanual_vr_teleop.gif
    Bimanual Robot Arm VR Teleopeariton
    Junsu Kim, Tai Inui, and Uksang Yoo
    CMU Research Internship, 2024
  4. Vision
    fipi.png
    Fisheye-Pinhole Camera Fusion for Multi-view 3D Object Detection
    Junsu Kim
    42dot Intership, 2024
  5. Simulation
    cpwc.gif
    DeepPAVE: Deep learning-based Personalized Autonomous VehiclE
    Team HAVI (Project leader)
    The 9th Cloud ProgrammingWorld Cup, 2021
    🏆Honorable Judge Award