Join Our Lab
PhD/MS Openings
We are recruiting self-motivated prospective students interested in impactful research across computer vision and spatial AI.
Research Areas:
LiDAR Localization
Our research centers on learning-based 3D localization, which aims to infer precise 3D poses using deep learning techniques. Among various approaches, we explore Scene Coordinate Regression (SCR): a method that predicts dense or sparse 3D scene points directly from sensor data like 2D images (camera) or 3D scans (LiDAR, Radar). Not only limited to single modality approaches, we explore sensor-fusion based localization methods to remain robust against outdoor environment.
Cross-View Localization
Cross-view localization is a computer vision problem that estimates the location and orientation of a ground-level camera by matching ground-view images with aerial or satellite maps. It is challenging because the two views are captured from drastically different perspectives, causing significant changes in appearance, scale, geometry, and visible structures. This field combines deep visual representation learning, cross-view image matching, and geometric pose estimation. It has important applications in autonomous driving, mobile robotics, navigation systems, and geo-spatial AI, especially when GPS signals are unavailable, inaccurate, or unreliable. In the future, this research will be extended beyond image-to-satellite localization toward LiDAR-cross-view localization and UAV-cross-view localization.
Privacy-Preserving Localization
Our lab conducts research in 3D Vision, Visual Localization, Geometric Vision, and Spatial AI. Recently, we have been expanding our research on Privacy-Preserving Visual Localization, which aims to estimate camera poses without exposing original images or sensitive visual information. We are looking for new students who are interested in studying geometric obfuscation, secure image query representations, and privacy-preserving localization algorithms. This research aims to enable the safe use of camera-based Spatial AI services in applications such as AR, robotics, autonomous driving, and digital twins. Students with interests in 3D Vision, Visual Localization, Deep Learning, Geometry, Optimization, and Privacy-Preserving AI are welcome to apply.
Requirements:
- Above 3.5/4.5 GPA from a renowned university
- Major in electrical/electronic engineering or computer science
- Experience in computer vision, machine learning, or related areas