I am an Assistant Professor at the School of Energy Engineering and Institute for Energy AI at KENTECH. Before joining KENTECH, I was a postdoctoral researcher at Bot Intelligence Group, Robotics Institute, CMU with Prof. Jean Oh. I obtained my Ph.D. and M.S. at KAIST, advised by Professor In So Kweon. I am a recipient of the Best Student Paper Award from WACV 2023, 29th Samsung Humantech Paper Award, 1st Place Award at 2024 CVPR WAD workshop, and Best Poster Award at 2025 ICRA TIRO workshop. Also, I co-organized “Thermal Infrared in Robotics” workshop in ICRA 2025 and “Multi-spectral Imaging for Robotics and Automation” workshop in ICCV 2025.
My research focuses on developing a robust physical AI that can perceive, understand, and navigate the dynamic world in challenging conditions, with a specific interest in spatial/semantic perception in extreme conditions, self-supervised learning, deep reinforcement learning, multi-sensor fusion, and vision-language navigation/manipulation. I am interested in the following areas, but also open to other explorable/challenging domains.
shinwc159 [at] gmail.com
ushin [at] kentech.ac.kr
KENTECH, 21 KENTECH-gil, Naju-si, Jeonnam 58330, Republic of Korea
Ph.D. in Electrical Engineering, KAIST, 2023
Advisor: Prof. In So Kweon
M.S. in Electrical Engineering, KAIST, 2019
Advisor: Prof. In So Kweon
B.S. in Electrical and Information Engineering, SNUST, 2017
Advisor: Prof. Byoung Wook Choi
All-day Depth Completion via Thermal-LiDAR Fusion
Under-review, 2025
Short version at 'Thermal Infrared in Robotics' workshop @ ICRA 2025
VPOcc: Exploiting Vanishing Point for Monocular 3D Semantic Occupancy Prediction
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025 Oral
Short version at 'Foundation Models for V2X-based Cooperative Autonomous Driving' workshop @ CVPR 2025
Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimatoin
IEEE Robotics and Automation Letters (RA-L), 2025
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025 Oral
1st Place Award, CVPR 2024 Autonomous Driving Workshop 'Argoverse Scene Flow Challenge'
Exploiting Cross-modal Cost Volume for Multi-sensor Depth Estimation
Asian Conference on Computer Vision (ACCV), 2024
[ paper ]
Density-aware Domain Generalization for LiDAR Semantic Segmentation
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024 Oral
[ paper ]
Learning Quadrupedal Locomotion with Impaired Joints Using Random Joint Masking
IEEE International Conference on Robotics and Automation (ICRA), 2024 Oral
Media coverage: covered by IEEE Spectrum
Stable Surface Regularization for Fast Few-Shot NeRF
International Conference on 3D Vision (3DV), 2024
[ paper ]
Deep Depth Estimation from Thermal Image
Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2023
[ paper / Benchmark / MS2 dataset / Github ]
Vehicular multi-camera sensor system for automated visual inspection of electric power distribution equipment
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019 Oral
Media coverage: covered by MBN, EnergyDaily, and many local media
[ paper ]
Performance evaluation of real-time mechanisms on open embedded hardware platforms
Journal of Institute of Control, Robotics and Systems, 2017
[ paper ]
Development and control of an omnidirectional mobile robot on an ethercat network
International Journal of Applied Engineering Research, 2016
[ paper ]