UniGeoRS：面向三视角地理定位的统一基准
UniGeoRS: A Unified Benchmark for Tri-view Geo-Localization
提供了卫星-无人机-地面三平台统一的地理定位基准与训练数据，并给出 CAME 这一可插拔的候选重排序模块——通过动态聚合 top-ranked 候选的上下文来精炼特征，可直接套用到现有跨视角检索/匹配流程中提升鲁棒性。
原文依据 we introduce the Unified Geo-localization dataset with Real-world and Synthetic imagery (UniGeoRS)
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论跨视角地理定位（CVGL）旨在通过将图像与来自不同视角的带地理参考图像进行匹配来估计该图像的地理位置，支撑自动驾驶、无人机导航和视觉监控等应用。然而，由于图像采集成本高昂，现有 CVGL 数据集在无人机与地面影像的多样性上往往不足，从而制约了模型的泛化能力。此外，现有方法主要聚焦于地面到卫星或无人机到卫星的匹配，缺乏一个能够处理卫星、无人机和地面这三个平台之间图像匹配的统一框架。为此，我们提出了统一地理定位数据集 UniGeoRS（Unified Geo-localization dataset with Real-world and Synthetic imagery），这是一个涵盖卫星、无人机和地面视角图像的综合基准，尤其强调无人机与地面视角的丰富性和多样性，从而支持更真实、更灵活的 CVGL 评测。此外，我们提出了基于交叉注意力的匹配增强框架 CAME，作为 CVGL 的统一框架。CAME 通过动态聚合排名靠前候选的上下文信息来精炼特征表示，并增强跨视角匹配的鲁棒性。实验结果表明：（1）所提出的 UniGeoRS 基准对于在三个平台上训练和评测 CVGL 模型是必要的；（2）UniGeoRS 提升了模型在多样条件下的泛化能力；（3）CAME 在最优的 CVGL 方法上均能稳定带来性能提升。
英文原文摘要 1559 字符
Cross-view geo-localization (CVGL) aims to estimate an image's geographic location by matching it with geo-referenced images from different viewpoints, supporting applications such as autonomous driving, UAV navigation, and visual surveillance. However, due to the high cost of image collection, current CVGL datasets often suffer from limited diversity in both drone and ground imagery, which constrains model generalization. Furthermore, existing methods primarily focus on either ground-to-satellite or drone-to-satellite matching, lacking a unified framework capable of handling image matching across all three platforms: satellite, drone, and ground. To this end, we introduce the Unified Geo-localization dataset with Real-world and Synthetic imagery (UniGeoRS), a comprehensive benchmark featuring satellite, drone, and ground-view images, with a particular emphasis on the richness and diversity of drone and ground perspectives, enabling more realistic and flexible evaluations of CVGL. Additionally, we propose Cross-Attention-based Matching Enhancement (CAME), a unified framework for CVGL. By dynamically aggregating contextual information from top-ranked candidates, CAME refines feature representations and enhances cross-view matching robustness. Experimental results show (1) The Proposed UniGeoRS benchmark is necessary for training and evaluating the CVGL model across all three platforms. (2) UniGeoRS improves model generalization across diverse conditions. (3) CAME consistently boosts performance across state-of-the-art CVGL approaches.