Sanghun Jung

University of Washington. Seattle. shjung13 [at] cs.washington.edu

SanghunJung_main.jpg

I am a fourth-year PhD candidate at the University of Washington, where I am advised by Byron Boots. I am interested in visual learning for robotics, bridging the gap between visual perception and robot planning/control. My recent research covers general robot perceptions problems in robot navigation including vision-language to navigation, traversability prediction from visual cues by self-supervision and representation learning from LiDAR and images.

Before starting Ph.D., I earned my M.S. from KAIST, and B.S. from Korea University. I worked at Bear Robotics for two years as a robotics engineer.

News

Feb 19, 2026 I successfully passed the Ph.D. Candidacy Exam!
Feb 19, 2026 I will be joining Waymo Perception Foundation Model team as a Research Scientist Intern this Summer 2026!
Feb 19, 2026 Personal web page updated!

Selected Publications

  1. SCNP.png
    Uncertainty-aware Accurate Elevation Modeling for Off-road Navigation via Neural Processes
    Sanghun Jung, Daehoon Gwak, Byron Boots, and 1 more author
    In Proceedings of The 9th Conference on Robot Learning, 2025
  2. OV3DIS.jpeg
    Details matter for indoor open-vocabulary 3D instance segmentation
    Sanghun Jung, Jingjing Zheng, Ke Zhang, and 8 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025
  3. traversability.png
    V-strong: Visual self-supervised traversability learning for off-road navigation
    Sanghun Jung, JoonHo Lee, Xiangyun Meng, and 2 more authors
    In IEEE International Conference on Robotics and Automation (ICRA), 2024
  4. cafa.png
    Cafa: Class-aware feature alignment for test-time adaptation
    Sanghun Jung, Jungsoo Lee, Nanhee Kim, and 3 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
  5. lidaruda.png
    Lidar-uda: Self-ensembling through time for unsupervised lidar domain adaptation
    Amirreza Shaban*, JoonHo Lee*, Sanghun Jung*, and 2 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
  6. SML.png
    Standardized max logits: A simple yet effective approach for identifying unexpected road obstacles in urban-scene segmentation
    Sanghun Jung*, Jungsoo Lee*, Daehoon Gwak, and 2 more authors
    In Proceedings of the IEEE/CVF international conference on computer vision, 2021
  7. RobustNet.png
    Robustnet: Improving domain generalization in urban-scene segmentation via instance selective whitening
    Sungha Choi*, Sanghun Jung*, Huiwon Yun, and 3 more authors
    In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021