Learning Cross-view Correspondences for Geo-localization on Planetary Surfaces
For planetary rovers lacking GPS, this work provides a first benchmark and proof that learning-based cross-view localization can work on planetary surfaces, though it is an incremental application of existing methods to a new domain.
The authors introduce a cross-view geo-localization benchmark for planetary surfaces, using physically rendered lunar panoramas and overhead tiles, and show that a transformer-based method achieves successful retrieval accuracy, offering a vision-based alternative to satellite navigation.
Maintaining global position awareness is a fundamental challenge for planetary surface exploration, since satellite-based positioning systems are unavailable and onboard odometry drifts over time. Although orbital mapping products, such as overhead imagery and terrain-derived maps, provide global context, aligning them with surface observations is challenging due to large viewpoint differences, low texture, repetitive terrain, and drastic changes in appearance caused by varying illumination and topography. We introduce a new cross-view geo-localization benchmark built from physically rendered surface panoramas and overhead tiles derived from a high-resolution lunar terrain model. Our dataset contains 10438 ground views rendered as 360$^\circ$ surface panoramas with matching overhead images precisely centered at the same location. Additionally, a set of overlapping tiles is provided to study off-center localization with multiple plausible candidates per panorama. We study the performance of a state-of-the-art transformer-based geo-localization method on our data, by training it from scratch and reporting retrieval accuracy. Our results demonstrate that learning-based cross-view localization methods can be successfully applied to the domain of planetary surfaces, providing a vision-based alternative to global navigation satellite systems.