Byeong-Uk Lee

Deep Learning Researcher @ KRAFTON, Inc.

byeonguk.lee [at] krafton.com

[CV] [Google Scholar]

Research Interests

3D Understanding - Sensor Fusion, 3D Reconstruction, Object Pose Estimation
3D Generation - Neural Radiance Field, Image to 3D, Avatar Generation
Computational Photography - Image Enhancement, 3D-Aware Image Editing, 3D Photography
Deep Learning - Learning Techniques for Computer Vision (ex. Self-Supervised Learning, Domain Adaptation)

Education

Korea Advanced Institute of Science and Technology (KAIST), South Korea
- Ph.D. in Electrical Engineering / Mar. 2019 - Aug. 2023
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

KRAFTON Inc, South Korea
- Deep Learning Researcher / Aug. 2023 - Present
- Advisor: Kangwook Lee
Adobe Research, San Jose CA, USA (Remote)
- Research Intern / July 2022 - Nov. 2022
- Advisor: Jianming Zhang
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 - Aug. 2023
- Advisor: In So Kweon

Publication

Learning to Control Camera Exposure via Reinforcement Learning

Kyunghyun Lee, Ukcheol Shin and Byeong-Uk Lee

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2024

[paper]

Stable Surface Regularization for Fast Few-Shot NeRF

ByeongIn Joung, Byeong-Uk Lee, Jaesung Choe, Ukcheol Shin, Minjun Kang, Taeyeop Lee, In-So Kweon and Kuk-Jin Yoon

International Conference on 3D Vision (3DV), Mar. 2024

[paper]

Single View Scene Scale Estimation using Scale Field

Byeong-Uk Lee, Jianming Zhang, Yannick Hold-Geoffroy and In So Kweon

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2023

[paper]

TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

Taeyeop Lee, Jonathan Tremblay, Valts Blukis, Bowen Wen, Byeong-Uk Lee, Inkyu Shin, Stan Birchfield, In So Kweon and Kuk-Jin Yoon

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2023

[paper]

Self-Supervised Monocular Depth Estimation From Thermal Images via Adversarial Multi-Spectral Adaptation

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

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (Best Student Paper), Jan. 2023

[paper] [code]

Maximizing Self-supervision from Thermal Image for Effective Self-supervised Learning of Depth and Ego-motion

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

IEEE Robotics and Automation Letters (RA-L), July 2022

[paper] [code]

UDA-COPE: Unsupervised Domain Adaptation for Category-Level Object Pose Estimation

Taeyeop Lee, Byeong-Uk Lee, Inkyu Shin, Jaesung Choe, Ukcheol Shin, In So Kweon and Kuk-Jin Yoon

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022

[paper]

Category-Level Metric Scale Object Shape and Pose Estimation

Taeyeop Lee, Byeong-Uk Lee, Myungchul Kim and In So Kweon

IEEE Robotics and Automation Letters (RA-L), Sep. 2021

[paper]

A Large-scale Virtual Dataset and Egocentric Localization for Disaster Responses

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

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), July 2021

[paper]

Depth Completion using Plane-Residual Representation

Byeong-Uk Lee, Kyunghyun Lee and In So Kweon

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021

[paper]

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), Dec. 2020

[paper] [code]

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) (Oral Presentation), May 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) (Oral Presentation), Nov. 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) (Oral Presentation), May 2019

[paper]