Year: 2022
Type: dissertation
Abstract: Visual localization is the task of determining the camera pose of a query image with respect to a 3D environment. The rapid development of deep learning has led to significant improvement of the existing methods meanwhile opened up several new options for tackling localization. This thesis focuses on investigating and understanding the potentials and limitations of the existing learning-based localization as well as developing new data-driven solutions to address the remaining challenges.
Authors: Zhou, Qunjie, Leal-Taixé, Laura, Technische Universität München
Institution: Technical University of Munich
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G176604203, G5916014575
OpenAlex ID: W6990256766
