Scholar

Jihun Kim

Google Scholar ID: 8UVicysAAAAJ

KAIST

computer vision3d visionfoundation model

Citations & Impact

All-time

Citations

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

6 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

Published 'DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation' at ICCV 2025
Published 'Multi-View 3D Scene Abstraction from Drone-Captured RGB Images' in IEEE Access
Published 'TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight' at NeurIPS 2024
Published 'Syn-to-Real Domain Adaptation for Point Cloud Completion via Part-based Approach' at ECCV 2024
Published 'Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle' at CVPR 2024
Published 'Learning Point Cloud Completion without Complete Point Clouds: A Pose-aware Approach' at ICCV 2023
2017: KAIST Dean’s List
2021: KAIST magna cum laude

Background

PhD candidate at Korea Advanced Institute of Science and Technology (KAIST), advised by Prof. Kuk-Jin Yoon
Member of the Visual Intelligence Lab (VILab)
Focuses on advancing environmental data understanding and prediction using minimal or weak annotations to reduce annotation burden
Works on tasks including semantic segmentation, data completion, and domain adaptation
Experienced with multiple data modalities such as images and point clouds (LiDAR)

Co-authors

5 total