Byeong-Uk Lee

Ph.D. Candidate

Robotics and Computer Vision Lab.

Korea Advanced Institute of Science and Technology (KAIST)

byeonguk.lee [at] kaist.ac.kr

[CV] [Google Scholar]

Research Interests

  • Computer Vision - 3D Reconstruction, Image Enhancement

  • Machine Learning - Deep Learning, Machine Learning for Computer Vision and Robotics

  • Robot Vision - Visual Odometry, SLAM, Robot Vision for Disaster-Relief

Education

  • Korea Advanced Institute of Science and Technology (KAIST), South Korea

    • Ph.D. candidate in Electrical Engineering Mar. 2019 - Present

  • Korea Advanced Institute of Science and Technology (KAIST), South Korea

    • M.S. in Electrical Engineering Mar. 2017 - Feb. 2019

  • Korea Advanced Institute of Science and Technology (KAIST), South Korea

    • B.S., Major in Electrical Engineering, Minor in Computer Science Mar. 2013 - Feb. 2017

Research Experience

  • The Robotics Institute, Carnegie Mellon University, Pittsburgh PA, USA

    • Visiting Researcher June 2019 - Aug. 2019

    • Advisor: Jean Oh, Martial Hebert

  • Robotics and Computer Vision Lab, KAIST, South Korea

    • Graduate Student Researcher Mar. 2017 - Present

    • Advisor: In So Kweon

Publication

An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search

Kyunghyun Lee, Byeong-Uk Lee, Ukcheol Shin and In So Kweon

Neural Information Processing Systems (NeurIPS) (Oral Presentation), 2020

[paper]

CNN-Based Simultaneous Dehazing and Depth Estimation

Byeong-Uk Lee, Kyunghyun Lee, Jean Oh and In So Kweon

IEEE International Conference on Robotics and Automation (ICRA), 2020

[paper]

DISC: A Large-scale Virtual Dataset for Simulating Disaster Scenarios

Hae-Gon Jeon, Sunghoon Im, Byeong-Uk Lee, Dong-Geol Choi, Martial Hebert and In So Kweon

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019

[paper]

Depth Completion with Deep Geometry and Context Guidance

Byeong-Uk Lee, Hae-Gon Jeon, Sunghoon Im and In So Kweon

IEEE International Conference on Robotics and Automation (ICRA), 2019

[paper]