The CVACT dataset is a matching task between street- and aerial views, from Canberra (Australia). This task helps to determine localization without GPS coordinates for the street-view images. Google Street View panoramas are used as ground images, and matching aerial images also from the Google Maps API. The dataset comprises 35,532 image pairs for training and 8,884 image pairs for evaluation, and recall is the primary metric for evaluation. To further test the generalization in comparison to the CVUSA dataset, CVACT features 92,802 test images.
Paper | Code | Results | Date | Stars |
---|