Wrivinder: Towards Spatial Intelligence for Geo-locating Ground Images onto Satellite Imagery

TL;DR

Wrivinder is a geometry-driven framework that aligns ground images with satellite maps using 3D reconstruction and semantic cues, achieving sub-30 meter accuracy without supervision.

Contribution

It introduces Wrivinder, a zero-shot method for cross-view geo-localization, and MC-Sat, a new dataset for benchmarking ground-to-satellite alignment.

Findings

Achieves sub-30 meter geolocation accuracy in zero-shot tests.

Provides a new dataset, MC-Sat, for benchmarking cross-view localization.

Demonstrates robustness across diverse outdoor environments.

Abstract

Aligning ground-level imagery with geo-registered satellite maps is crucial for mapping, navigation, and situational awareness, yet remains challenging under large viewpoint gaps or when GPS is unreliable. We introduce Wrivinder, a zero-shot, geometry-driven framework that aggregates multiple ground photographs to reconstruct a consistent 3D scene and align it with overhead satellite imagery. Wrivinder combines SfM reconstruction, 3D Gaussian Splatting, semantic grounding, and monocular depth--based metric cues to produce a stable zenith-view rendering that can be directly matched to satellite context for metrically accurate camera geo-localization. To support systematic evaluation of this task, which lacks suitable benchmarks, we also release MC-Sat, a curated dataset linking multi-view ground imagery with geo-registered satellite tiles across diverse outdoor environments. Together, Wrivinder and MC-Sat provide a first comprehensive baseline and testbed for studying geometry-centered cross-view alignment without paired supervision. In zero-shot experiments, Wrivinder achieves sub-30\,m geolocation accuracy across both dense and large-area scenes, highlighting the promise of geometry-based aggregation for robust ground-to-satellite localization.