Jaeyeul Kim Jaeyeul Kim

Jaeyeul Kim

I am an assistant professor in the Division of Computer Engineering and Artificial Intelligence at Pukyong National University (PKNU), Busan, South Korea, where I lead the Robot Vision Lab.

Before joining PKNU in September 2026, I was a postdoctoral researcher at DGIST, South Korea, working on autonomous driving with Prof. Sunghoon Im at the DGIST Computer Vision Lab, where I received my Ph.D. in February 2026.

Specifically, I have worked on LiDAR-based segmentation, detection, tracking, and forecasting. My current research interest is in autonomous vehicle planning. From April to October 2024 I was a visiting researcher at the Robotics Institute, Carnegie Mellon University, Pittsburgh, US.

News

2026
2025
2024
2023
2022
2021

Publications

* indicates equal contribution. † indicates the corresponding author.

SPL 2026
Object-Centric LiDAR-to-Radar Distillation
Object-Centric LiDAR-to-Radar Distillation for 3D Object Detection
Sungho Moon*, Jaeyeul Kim*, Wonhyeok Choi, Jihun Park, Ukcheol Shin†, Sunghoon Im†
IEEE Signal Processing Letters (SPL), 2026
SIGGRAPH Asia 2026
CRAFT
CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without Composed Targets
Jihun Park, Kyoungmin Lee, Jongmin Gim, Hyeonseo Jo, Jaeyeul Kim, Han Zou, Zhenpeng Zhan, Yan Zhang†, Sunghoon Im†
ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH Asia), 2026
Oral Presentation
CVPR 2026
TaskForce
TaskForce: Cooperative Multi-agent Reinforcement Learning for Multi-task Optimization
Wonhyeok Choi, Kyumin Hwang, Jihun Park, Kyoungmin Lee, Seunghun Lee, Jaeyeul Kim, Minwoo Choi, Sunghoon Im†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
CVPR 2026
Style Personalization
A Training-Free Style-Personalization via SVD-Based Feature Decomposition
Kyoungmin Lee*, Jihun Park*, Jongmin Gim*, Wonhyeok Choi, Kyumin Hwang, Jaeyeul Kim, Sunghoon Im†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
AAAI 2026
Infinite-Story
Infinite-Story: A Training-Free Consistent Text-to-Image Generation
Jihun Park*, Kyoungmin Lee*, Jongmin Gim*, Hyeonseo Jo, Minseok Oh, Wonhyeok Choi, Kyumin Hwang, Jaeyeul Kim, Minwoo Choi, Sunghoon Im†
The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026
Oral Presentation
TOMM 2026
Noise-mined Adaptive Self-Labeling
Mitigating Noisy Correspondence in Video-Text Retrieval via Noise-mined Adaptive Self-Labeling
Jeonghoon Kim*, Hyeon Kang*, Jihun Park, Jinhwoi Kim, Jaeyeul Kim, Sunghoon Im†
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2026
SPL 2026
CascadeOcc
CascadeOcc: Rethinking 3D Occupancy World Models with Cascaded VQ Representations
Kyumin Hwang*, Wonhyeok Choi*, Jaeyeul Kim, Jihun Park, Daehee Park†, Sunghoon Im†
IEEE Signal Processing Letters (SPL), 2026
ICEIC 2026
BriGeS
Bridging Geometric and Semantic Foundation Models for Generalized Monocular Depth Estimation
Sanggyun Ma*, Wonjoon Choi*, Jihun Park*, Jaeyeul Kim, Seunghun Lee, Jiwan Seo, Sunghoon Im†
The 25th International Conference on Electronics, Information, and Communication (ICEIC), 2026
ICCVw 2025
Semantic-Enhanced Monocular Depth Estimation
Semantic-Enhanced Monocular Depth Estimation via Fusion and Distillation of Foundation Models
Sanggyun Ma*, Wonjoon Choi*, Jihun Park, Jaeyeul Kim, Sunghoon Im†
International Conference on Computer Vision Workshop (ICCVw), 2025
RA-L / IROS 2025
Flow4D
Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation
Jaeyeul Kim, Jungwan Woo, Ukcheol Shin, Jean Oh, Sunghoon Im
IEEE Robotics and Automation Letters (RA-L / IROS), 2025
Winner of the Argoverse 2 LiDAR Scene Flow Challenge at CVPR 2024 WAD
arXiv Preprint
Style-aligned Scale-wise Autoregressive Generation
A Training-Free Style-aligned Image Generation with Scale-wise Autoregressive Model
Jihun Park*, Jongmin Gim*, Kyoungmin Lee*, Minseok Oh, Minwoo Choi, Jaeyeul Kim, Woochool Park, Yan Zhang, Zhenpeng Zhan, Sunghoon Im†
arXiv Preprint, 2025
ECCV 2024
Rethinking LiDAR Domain Generalization
Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains
Jaeyeul Kim*, Jungwan Woo*, Jeonghoon Kim, Sunghoon Im
European Conference on Computer Vision (ECCV), 2024
IROS 2024
Density-aware Domain Generalization
Density-aware Domain Generalization for LiDAR Semantic Segmentation
Jaeyeul Kim*, Jungwan Woo*, Ukcheol Shin, Jean Oh, Sunghoon Im
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
IEEE Access 2023
Automatic Extrinsic Calibration with Point-Line Correspondences
Automatic Extrinsic Calibration of a Camera and a 2D LiDAR with Point-Line Correspondences
Jaeyeul Kim, Jongeun Ha
IEEE Access, 2023
CVPRw 2023
Motion Forecasting via Coordinate Transformations
Motion Forecasting via Coordinate Transformations and Object Trajectory Modifications
Jungwan Woo*, Jaeyeul Kim*, Sunghoon Im
CVPR Workshop on Autonomous Driving (CVPRw), 2023
2nd place in the challenge
ECCVw 2022
LiDAR 3D Object Detection via Self-Training and Knowledge Distillation
LiDAR 3D Object Detection via Self-Training and Knowledge Distillation
Jungwan Woo*, Jaeyeul Kim*, Sunghoon Im
ECCV Workshop on 3D Perception for Autonomous Driving (ECCVw), 2022
3rd place in the challenge
IEEE Access 2022
Weakly Supervised Foreground Object Detection Network
Weakly Supervised Foreground Object Detection Network Using Background Model Image
Jaeyeul Kim, Jongeun Ha
IEEE Access, 2022
RA-L / IROS 2022
RVMOS
RVMOS: Range-View Moving Object Segmentation Leveraged by Semantic and Motion Features
Jaeyeul Kim*, Jungwan Woo*, Sunghoon Im
IEEE Robotics and Automation Letters (RA-L / IROS), 2022
IEEE Access 2021
Spatio-temporal Data Augmentation for Visual Surveillance
Spatio-temporal Data Augmentation for Visual Surveillance
Jaeyeul Kim, Jongeun Ha
IEEE Access, 2021
IEEE Access 2021
Generation of Background Model Image Using Foreground Model
Generation of Background Model Image Using Foreground Model
Jaeyeul Kim, Jongeun Ha
IEEE Access, 2021
IEEE Access 2020
Extrinsic Calibration using a Dummy Camera
Extrinsic Calibration of a Camera and a 2D LiDAR using a Dummy Camera with IR Cut Filter Removed
Jaeyeul Kim, Jongeun Ha
IEEE Access, 2020
IEEE Access 2020
Foreground Objects Detection Using a Fully Convolutional Network
Foreground Objects Detection Using a Fully Convolutional Network with a Background Model Image and Multiple Original Images
Jaeyeul Kim, Jongeun Ha
IEEE Access, 2020
ICCAS 2019
Automatic Extrinsic Calibration of a Camera and Laser Range Finder using Constraints Fusion
Jaeyeul Kim, Jongeun Ha
International Conference on Control, Automation and Systems (ICCAS), 2019
ICCAS 2018
Extrinsic Calibration of Camera and Laser Range Finder using a Dummy Camera without IR Cut Filter
Jaeyeul Kim, Jongeun Ha
International Conference on Control, Automation and Systems (ICCAS), 2018

Education & Research Experience

Assistant Professor

Division of Computer Engineering and Artificial Intelligence, Pukyong National University (PKNU), Busan, South Korea

Sep. 2026 – Present

Postdoctoral Researcher

Daegu Gyeongbuk Institute of Science and Technology (DGIST), South Korea

Feb. 2026 – Aug. 2026

Visiting Researcher

Robotics Institute, Carnegie Mellon University (CMU), Pittsburgh, US

Apr. 2024 – Oct. 2024

Ph.D. in Electrical Engineering and Computer Science (Advisor: Sunghoon Im)

Daegu Gyeongbuk Institute of Science and Technology (DGIST), South Korea

Aug. 2021 – Feb. 2026

M.S. in Automotive Engineering (Advisor: Jongeun Ha)

Seoul National University of Science and Technology (SEOULTECH), South Korea

Aug. 2018 – Aug. 2021

B.S. in Mechanical and Automotive Engineering

Seoul National University of Science and Technology (SEOULTECH), South Korea

Mar. 2012 – Aug. 2018

Academic Activities

Scholarships & Awards
Reviewer
Skills
Other Experience