InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization

Cross-view geo-localization (CVGL) is fundamental for precise localization and navigation in GPS-denied environments, aiming to match ground or UAV imagery with satellite views. Existing approaches often rely on global feature alignment, but they suffer from substantial domain shifts induced by varying regional textures and weather conditions. This issue becomes even more pronounced in UAV-based scenarios, where the broader perspective inevitably introduces dense, fine-grained objects, creating significant visual clutter. To address this, we draw inspiration from Object-Centric Learning (OCL) and propose InfoGeo, an information-theoretic framework designed to enhance robustness and generalization. InfoGeo reformulates the optimization as an information bottleneck process with two core objectives: (i) maximizing view-invariant information by aligning the object-centric structural relations across views, and (ii) minimizing view-specific noisy signals through cross-view knowledge constraints. Extensive evaluations across diverse benchmarks and challenging scenarios demonstrate that InfoGeo significantly outperforms state-of-the-art methods.

Accurately localizing camera images is essential for UAV autonomous systems and navigation, especially when GPS is unreliable or unavailable. A common approach is to match a ground or drone image with a satellite image of the same place. However, this is challenging because the same location can look very different across views due to weather, lighting, regional appearance, and camera perspective. Drone images make the task even harder, as they often contain many small objects (e.g., cars, trees), which can distract the model. We propose InfoGeo, a method that helps models focus on useful location cues rather than distracting visual details. Instead of comparing only overall appearance, InfoGeo captures meaningful objects and their spatial relationships across views. It preserves information shared between different views while suppressing view-specific details that may cause confusion. By focusing on stable structures and reducing noisy information, InfoGeo makes geo-localization more reliable across diverse regions, weather conditions, and challenging drone-based scenarios.