I am a Ph.D. student advised by Prof. Kuk-Jin Yoon at Visual Intelligence Lab (VILab), Korea Advanced Institute of Science and Technology (KAIST). I am actively seeking a research intern position.

I am dedicated to advancing the understanding and prediction of environmental data through innovative approaches that utilize minimal or weak annotations, significantly reducing the annotation burden. I have tackled a range of tasks such as semantic segmentation, data completion, and domain adaptations. My expertise spans various data modalities, including images, and point cloud (LiDAR).

My CV can be found in here

Publications

TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight
H. Jang*, J. Kim*, H. Kweon*, K. Yoon
NeurIPS 2024
[paper]

Syn-to-Real Domain Adaptation for Point Cloud Completion via Part-based Approach
Y. Yang*, J. Kim*, K. Yoon
ECCV 2024
[paper]

Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle
H. Kweon*, J. Kim*, K. Yoon
CVPR 2024
[paper]

Learning Point Cloud Completion without Complete Point Clouds: A Pose-aware Approach
J. Kim, H. Kweon, Y. Yang, K. Yoon
ICCV 2023
[paper]

Selected Honors and Awards

• 2017 / KAIST Dean’s List
  

Projects

• 2021 ~ 2022 / Autonomous ship collision and accident prevention situation awareness system / object detection, object tracking, and data labeling
  
• 2023 ~ 2024 / Surround view depth estimation for autonomous vehicle systems / depth estimation, self-supervised learning, and surround view reconstruction
  
• 2024 ~ present/ Unmanned Swarm CPS Research Laboratory Program of Defense Acquisition Program / drone imaging, image stitching, 3D reconstruction, and point cloud semantic segmentation