Scholar
Kwon Byung-Ki
Google Scholar ID: rUmP7vgAAAAJ
POSTECH
Citations & Impact
Citations
15
H-index
3
i10-index
0
Publications
9
Co-authors
7
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publication: JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers, ICCV 2025
- Publication: Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior, AAAI 2025
- Publication: Learning-based Axial Video Motion Magnification, ECCV 2024
- Publication: Revisiting Deep Video Motion Magnification for Real-time Applications, Under review
- Publication: Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation, RA-L 2024
- Publication: The Devil is in the Details: Simple Remedies for Image-to-LiDAR Representation Learning, ACCV 2024
- Publication: DFlow: Learning to Synthesize Better Optical Flow datasets via a Differentiable Pipeline, ICLR 2023
- Publication: The Devil in the Details: Simple and Effective Optical Flow Data Generation, TVCJ 2024
- Award: Outstanding Reviewer Award, ICCV 2023
- Award: Samsung HumanTech Paper Award, 2023 ($5,000)
- Award: Best Paper Award, Asian Federation of Computer Vision (AFCV), 2024
- Award: Best Paper Award, Workshop on Image Processing and Image Understanding (IPIU), 2023
- Award: Best Paper Award, Workshop on Image Processing and Image Understanding (IPIU), 2021
Background
- Ph.D. Student in Algorithmic Machine Learning (AMI) Lab, Dept. of Artificial Intelligence, POSTECH, South Korea. Research interests include 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.
Miscellany
- Contact: byungki.kwon[at]postech[dot]ac[dot]kr
