Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation
*Authors contributed equally to this work.
CVPR, 2025
Junha Lee
I am a Ph.D. student in the Computer Vision Lab at POSTECH, supervised by Minsu Cho. Previously, I completed my M.S. and B.S. in Computer Science and Engineering department at POSTECH.
My research interests lie in the intersection of 3D computer vision and deep learning. I've worked on the neural rendering and implicit representation, efficient 3D perception network architectures, correspondence estimation for images and point clouds.
Publications
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
- [
- paper
- ]
PeRFception: Perception using Radiance Fields
*Authors contributed equally to this work.
NeurIPS Track on Datasets and Benchmarks, 2022
Putting 3D Spatially Sparse Networks on a Diet
Preprint. 2021
- [
- paper
- ]
Deep Hough Voting for Robust Global Registration
ICCV, 2021
High Dimensional Convolutional Networks for Geometric Pattern Recognition
CVPR, 2020
*Oral presentation, 5.7% acceptance rate
Services
- Reviewer in CVPR (2022-2025), ECCV(2022,2024), ICCV (2021,2023,2025), BMVC (2021), IEEE RA-L/ICRA (2021)