Junha Lee
Scholar

Junha Lee

Google Scholar ID: RB7qMm4AAAAJ
POSTECH
Computer Vision
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
244
 
H-index
4
 
i10-index
3
 
Publications
9
 
Co-authors
0
 
Contact
Emailjunhakiwi@postech.ac.krCVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
6 items
LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models
2026
Cited
0
SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation
2026
Cited
0
DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning
2026
Cited
0
Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments
2025
Cited
0
Affogato: Learning Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale
2025
Cited
0
Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation
2025
Cited
0
Resume
Academic Achievements
  • Publications:
  • - Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation (CVPR, 2025)
  • - 3D Geometric Shape Assembly via Efficient Point Cloud Matching (ICML, 2024)
  • - Learning to Register Unbalanced Point Pairs (CVPR 2023 - Workshop on 3D Vision and Robotics)
  • - PeRFception: Perception using Radiance Fields (NeurIPS Track on Datasets and Benchmarks, 2022)
  • - Putting 3D Spatially Sparse Networks on a Diet (Preprint, 2021)
  • - Deep Hough Voting for Robust Global Registration (ICCV, 2021)
  • - High Dimensional Convolutional Networks for Geometric Pattern Recognition (CVPR, 2020)
  • Reviewer experience: CVPR (2022-2025), ECCV(2022,2024), ICCV (2021,2023,2025), BMVC (2021), IEEE RA-L/ICRA (2021)
Research Experience
  • Conducted Ph.D. research in the Computer Vision Lab at POSTECH, working on multiple 3D vision and deep learning projects.
Education
  • Ph.D. student in the Computer Vision Lab at POSTECH, supervised by Minsu Cho; M.S. and B.S. in Computer Science and Engineering department at POSTECH.
Background
  • Research interests: the intersection of 3D computer vision and deep learning. Worked on neural rendering and implicit representation, efficient 3D perception network architectures, correspondence estimation for images and point clouds.