no code implementations • 25 Sep 2019 • Moti Kadosh, Yael Moses, Ariel Shamir
In this paper we consider the geo-localization task - finding the pose of a camera in a large 3D scene from a single lean image, i. e. an image with no texture.
no code implementations • 26 Jun 2019 • Moti Kadosh, Yael Moses, Ariel Shamir
We find that the network is capable of estimating the camera pose from the lean images, and it does so not by memorization but by some measure of geometric learning of the geographical area.