I am currently a final-year PhD candidate at the Intelligent Vehicles group at TU Delft, under the supervision of Dr. Julian F. P. Kooij and Prof. Dr. Dariu M. Gavrila. My PhD project is funded by the Dutch Research Council Efficient Deep Learning project. My primary research area is ground-to-aerial visual localization for autonomous vehicles. I have a keen interest in mapping and localization, 3D computer vision, representation learning, and self-supervised learning. Throughout my PhD journey, I’ve had the privilege to collaborate with TomTom in Amsterdam.

Prior to my PhD pursuit, I completed my MSc in Geomatics Engineering at the University of Stuttgart, Germany, in 2019, and received my BSc in Geodesy and Geomatics Engineering from Wuhan University, China, in 2016.

Selected publications

Convolutional Cross-View Pose Estimation
Zimin Xia, Olaf Booij, Julian F. P. Kooij
Accepted by T-PAMI
Paper | Code

SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation
Ted Lentsch*, Zimin Xia*, Holger Caesar, Julian F.P. Kooij
*:Equal contribution
CVPR 2023
Paper | Code | Video

Visual cross-view metric localization with dense uncertainty estimates
Zimin Xia, Olaf Booij, Marco Manfredi, Julian F.P. Kooij
ECCV 2022
Paper | Code | Video

Cross-view matching for vehicle localization by learning geographically local representations
Zimin Xia, Olaf Booij, Marco Manfredi, Julian F.P. Kooij
IEEE RA-L 2021
Paper | Code | Video

Geographically local representation learning with a spatial prior for visual localization
Zimin Xia, Olaf Booij, Marco Manfredi, Julian F.P. Kooij
ECCV Workshop 2020 (Oral)
Paper | Code | Video