Loc$^2$: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching
This addresses the problem of accurate and interpretable localization for applications such as navigation or mapping, though it appears incremental as it builds on prior methods by introducing a new matching and depth-lifting approach.
The paper tackles the problem of fine-grained cross-view localization by estimating the 3 DoF pose of a ground-level image using local feature matching with a reference aerial image, achieving state-of-the-art accuracy in challenging scenarios like cross-area testing and unknown orientation.
We propose an accurate and interpretable fine-grained cross-view localization method that estimates the 3 Degrees of Freedom (DoF) pose of a ground-level image by matching its local features with a reference aerial image. Unlike prior approaches that rely on global descriptors or bird's-eye-view (BEV) transformations, our method directly learns ground-aerial image-plane correspondences using weak supervision from camera poses. The matched ground points are lifted into BEV space with monocular depth predictions, and scale-aware Procrustes alignment is then applied to estimate camera rotation, translation, and optionally the scale between relative depth and the aerial metric space. This formulation is lightweight, end-to-end trainable, and requires no pixel-level annotations. Experiments show state-of-the-art accuracy in challenging scenarios such as cross-area testing and unknown orientation. Furthermore, our method offers strong interpretability: correspondence quality directly reflects localization accuracy and enables outlier rejection via RANSAC, while overlaying the re-scaled ground layout on the aerial image provides an intuitive visual cue of localization accuracy.