On the role of geometry in geo-localization
geo-localization, geometry, CNN-based solutions, synthetic lean images
Consider the geo-localization task of finding the pose of a camera in a large 3D scene from a single image. Most existing CNN-based methods use as input textured images. We aim to experimentally explore whether texture and correlation between nearby images are necessary in a CNN-based solution for the geo-localization task. To do so, we consider lean images, textureless projections of a simple 3D model of a city. They only contain information related to the geometry of the scene viewed (edges, faces, and relative depth). The main contributions of this paper are: (i) todemonstrate the ability of CNNs to recover camera pose using lean images; and (ii) to provide insight into the role of geometry in the CNN learning process.
Tsinghua University Press
Moti Kadosh, Yael Moses, Ariel Shamir. On the role of geometry in geo-localization. Computational Visual Media 2021, 7(1): 103-113.