Search papers, labs, and topics across Lattice.
This paper introduces OffNadirLoc, a benchmark specifically designed for UAV-to-satellite geo-localization under large off-nadir views, addressing the limitations of existing methods that focus on near-nadir scenarios. The authors propose the ONLoc framework, which employs a structure-aware contextual weighting mechanism and a view-coherent learning strategy to enhance the model's ability to capture viewpoint-invariant features. Experimental results show that ONLoc significantly outperforms state-of-the-art methods and demonstrates strong zero-shot generalization capabilities to unseen datasets.
OffNadirLoc reveals that leveraging structure-aware contextual weighting can dramatically enhance UAV-to-satellite geo-localization performance under challenging off-nadir conditions.
Cross-view geo-localization between UAV and satellite imagery remains a fundamental yet highly challenging task, especially under large off-nadir views where drastic perspective distortions, occlusions, and appearance gaps occur. Existing benchmarks and methods primarily focus on near-nadir scenarios and often overlook the importance of structural scene understanding and intra-domain relational constraints, limiting their performance in real-world deployments. In this work, we introduce OffNadirLoc, a new benchmark for large off-nadir UAV-to-satellite geo-localization. To tackle the unique challenges posed by off-nadir perspectives, we further propose ONLoc, a framework that incorporates a structure-aware contextual weighting mechanism to dynamically emphasize reliable local features while suppressing ambiguous or repetitive regions. Additionally, we design a view-coherent learning strategy, which treats one satellite image and the corresponding UAV images from multiple views as a cohesive semantic group. This set-level supervision enables the model to learn viewpoint-invariant and discriminative features, making it more effective at capturing multi-view consistency than conventional pairwise contrastive learning. Extensive experiments on the OffNadirLoc benchmark and four near-nadir datasets demonstrate that our method consistently outperforms state-of-the-art approaches while exhibiting strong zero-shot generalization to unseen datasets without additional training. The code will be released at https://montalario.github.io/offnadirloc/.
