Scholar
Qunjie Zhou
Google Scholar ID: d5DqmRoAAAAJ
Nvidia
Citations & Impact
Citations
1,305
H-index
9
i10-index
9
Publications
17
Co-authors
7
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published several papers including DynOMo: Online Point Tracking by Dynamic Online Monocular Gaussian Reconstruction, Light3R-SfM: Towards Feed-forward Structure-from-Motion, MATCHA: Towards Matching Anything, Towards cross-modal pose localization from text-based position descriptions, Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization, Patch2Pix: Epipolar-Guided Pixel-Level Correspondences, To Learn or Not to Learn: Visual Localization from Essential Matrices, Understanding the Limitations of CNN-based Absolute Camera Pose Regression.
Research Experience
- Has been a research scientist at NVIDIA’s Dynamic Vision and Learning (DVL) group since 2023.
Education
- Earned a double B.Sc. degree in Electrical Engineering and Information Technology in 2015; Completed an M.Sc. in Computer Science at the Technical University of Munich (TUM) in 2018; Pursued her PhD under the supervision of Prof. Dr. Laura Leal-Taixé as part of the Dynamic Vision and Learning Group at TUM.
Background
- Research interests: Understanding 3D geometry in unconstrained environments; Specializes in advancing feature matching, camera pose estimation, and 3D reconstruction algorithms using deep learning techniques.
