Team
home
Professor
home

Prof. Seokju Lee

Title
Professor
Welcome! I am an assistant professor at the School of Energy Engineering and Institute for Energy AI at KENTECH, Korea. Before Joining KENTECH, I completed my Ph.D. degree in Aug. 2021 at KAIST under the supervision of Prof. In So Kweon, and the M.S. degree in Aug. 2015 at KAIST under the supervision of Prof. David Hyunchul Shim. I finished my B.S. degree in electrical and computer engineering from UNIST in 2013. I was a research intern in Visual Computing Group at Microsoft Research Asia (MSRA) during 2018, working with Dr. Stephen Lin. I am one of the winners of Qualcomm Innovation Fellowship 2020, and 16th Samsung Electro-Mechanics Best Paper Award as the first author.
Selected Publication (all 1st author papers)
- S. Lee, et al., “Self-supervised Monocular Depth and Motion Learning in Dynamic Scenes: Semantic Prior to Rescue”, International Journal of Computer Vision (IJCV), 2022. - S. Lee, et al., “Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation”, IEEE International Conference on Computer Vision (ICCV), 2021. - S. Lee, et al., “Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency”, AAAI Conference on Artificial Intelligence (AAAI), 2021. - S. Lee, et al., “Learning Residual Flow as Dynamic Motion from Stereo Videos”, IEEE International Conference on Intelligent Robots and Systems (IROS), 2019. - S. Lee, et al., “Visuomotor Understanding for Representation Learning of Driving Scenes”, British Machine Vision Conference (BMVC), 2019. - S. Lee, et al., “VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition”, IEEE International Conference on Computer Vision (ICCV), 2017.
Thesis
Ph.D. (KAIST, advisor: Prof. In So Kweon) “Learning-Based Visual Perception Using Semantic and Geometric Priors for Autonomous Driving”, Aug. 2021. link M.S. (KAIST, advisor: Prof. David Hyunchul Shim) “Hierarchical Pedestrian Detection Using Omnidirectional Camera and Laser Sensor Fusion”, Aug. 2015. link