15 papers with code • 2 benchmarks • 6 datasets
Determining the location of an image without GPS based on cross-view matching. In most of the cases a database of satellite images is used to match the ground images to them.
This paper tackles the problem of large-scale image-based localization (IBL) where the spatial location of a query image is determined by finding out the most similar reference images in a large database.
To our knowledge, University-1652 is the first drone-based geo-localization dataset and enables two new tasks, i. e., drone-view target localization and drone navigation.
In this work we design a deep neural network architecture based on sparse feature descriptors to estimate the absolute pose of an image.
This paper proposes a novel Cross-View Feature Transport (CVFT) technique to explicitly establish cross-view domain transfer that facilitates feature alignment between ground and aerial images.
Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas.
Domain-invariant Similarity Activation Map Contrastive Learning for Retrieval-based Long-term Visual Localization
Visual localization is a crucial component in the application of mobile robot and autonomous driving.
Long-Term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics due to season, illumination variance, etc.
We introduce the first general solution to the problem of estimating the pose of a calibrated camera given a single observation of an oriented point and an affine correspondence.
In this paper, we propose the first minimal solutions for estimating the semi-generalized homography given a perspective and a generalized camera.