Kwon Byung-Ki
Embedded Files
I am a Ph.D. Student in Algorithmic Machine Learning (AMI) Lab, Dept. of Artificial Intelligence, POSTECH, South Korea. I am advised by Prof. Tae-Hyun Oh. I finished my master's degree from AMILab in POSTECH, and bachelor's degree at POSTECH.
My research interests lie in low-level computer vision, such as optical flow estimation and depth estimation, and extending these techniques to image & video generative models.
Keywords: optical flow estimation, depth estimation, meta-learning, motion magnification, generative model, but not limited to
Contact: byungki.kwon[at]postech[dot]ac[dot]kr
Information: CV, Google Scholar, Linkedin
Work Experience
Research Internship, Microsoft Research Asia
Sep. 2024 – Mar. 2025
Education
Ph.D. of Artificial Intelligence (advisor: Tae-Hyun Oh)
Master of Electrical Engineering (advisor: Tae-Hyun Oh)
Bachelor of Mechanical Engineering
POSTECH, Mar. 2023
POSTECH, Sep. 2020 – Feb. 2023
POSTEDH, Mar. 2013 – Aug 2019
Publications
JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers, ICCV 2025
*Work performed while interning at Microsoft Research Asia (MSRA)
JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers, ICCV 2025
*Work performed while interning at Microsoft Research Asia (MSRA)
Kwon Byung-Ki, Qi Dai, Lee Hyoseok, Chong Luo, Tae-Hyun Oh
Kwon Byung-Ki, Qi Dai, Lee Hyoseok, Chong Luo, Tae-Hyun Oh
jointdit.mp4Zero-shot Depth Completion via Test-time Alignment
with Affine-invariant Depth Prior, AAAI 2025
Lee Hyoseok, Kyeong Seon Kim, Kwon Byung-Ki, Tae-Hyun Oh
Learning-based Axial Video Motion Magnification, ECCV 2024
Kwon Byung-Ki, Oh Hyun-Bin, Kim Jun-Seong, Ha Hyunwoo, Tae-Hyun Oh
axial_momag.mp4Revisiting Deep Video Motion Magnification for Real-time Applications, Under review
Ha Hyunwoo, Oh Hyun-Bin, Kim Jun-Seong, Kwon Byung-Ki, Kim Sung-Bin, Ji-Yun Kim, Sung-Ho Bae, Tae-Hyun Oh
realtime_mm.mp4Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation, RA-L 2024
Kim Ji-Yeon, Oh Hyun-Bin, Kwon Byung-Ki, Dahun Kim, Yongjin Kwon, Tae-Hyun Oh
The Devil is in the Details: Simple Remedies for Image-to-LiDAR Representation Learning, ACCV 2024
Jo Won-jun, Kwon Byung-Ki, Kim Ji-Yeon, Hawook Jeong, Kyungdon Joo, Tae-Hyun Oh
DFlow: Learning to Synthesize Better Optical Flow datasets via a Differentiable Pipeline, ICLR 2023
Kwon Byung-Ki, Nam Hyeon-Woo, Kim Ji-Yun, Tae-Hyun Oh
The Devil in the Details: Simple and Effective Optical Flow Data Generation, TVCJ 2024
Kwon Byung-Ki, Kim Sung-Bin, Tae-Hyun Oh
Awards
Outstanding Reviewer Award, ICCV 2023
Samsung HumanTech Paper Award, 2023 (5,000$)
Best Paper Award, Asian Federation of Computer VIsion (AFCV), 2024
Best Paper Award, Workshop on Image Processsing and Image Understanding (IPIU), 2023
Best Paper Award, Workshop on Image Processsing and Image Understanding (IPIU), 2021
Page updated
Google Sites
Report abuse