Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimation
This addresses geo-localization for applications like navigation and mapping, but it is incremental as it revisits an existing problem with a focus on metric learning and alignment effects.
The paper tackles street-to-aerial image geo-localization by showing that performance depends heavily on alignment assumptions and that metric learning improvements boost results regardless of alignment, outperforming previous works on panorama and cropped datasets and achieving state-of-the-art orientation estimation on CVUSA.
Street-to-aerial image geo-localization, which matches a query street-view image to the GPS-tagged aerial images in a reference set, has attracted increasing attention recently. In this paper, we revisit this problem and point out the ignored issue about image alignment information. We show that the performance of a simple Siamese network is highly dependent on the alignment setting and the comparison of previous works can be unfair if they have different assumptions. Instead of focusing on the feature extraction under the alignment assumption, we show that improvements in metric learning techniques significantly boost the performance regardless of the alignment. Without leveraging the alignment information, our pipeline outperforms previous works on both panorama and cropped datasets. Furthermore, we conduct visualization to help understand the learned model and the effect of alignment information using Grad-CAM. With our discovery on the approximate rotation-invariant activation maps, we propose a novel method to estimate the orientation/alignment between a pair of cross-view images with unknown alignment information. It achieves state-of-the-art results on the CVUSA dataset.