Abstract
Cross-view geo-localization infers a location by retrieving geo-tagged reference images that visually correspond to a query image. However, the traditional satellite-centric paradigm limits robustness when high-resolution or up-to-date satellite imagery is unavailable. It further underexploits complementary cues across views (e.g., drone, satellite, and street) and modalities (e.g., language and image). To address these challenges, we propose GeoBridge, a foundation model that performs bidirectional matching across views and supports language-to-image retrieval. Going beyond traditional satellite-centric formulations, GeoBridge builds on a novel semantic-anchor mechanism that bridges multi-view features through textual descriptions for robust, flexible localization. In support of this task, we construct GeoLoc, the first large-scale, cross-modal, and multi-view aligned dataset comprising over 50,000 pairs of drone, street-view panorama, and satellite images as well as their textual descriptions, collected from 36 countries, ensuring both geographic and semantic alignment. We performed broad evaluations across multiple tasks. Experiments confirm that GeoLoc pre-training markedly improves geo-location accuracy for GeoBridge while promoting cross-domain generalization and cross-modal knowledge transfer. The dataset, source code, and pretrained models were released at this https URL.
Abstract (translated)
跨视角地理定位通过检索与查询图像视觉上对应的地理标记参考图像来推断位置。然而,传统的以卫星为中心的范式在高分辨率或最新卫星影像不可用时会限制其鲁棒性,并且未能充分利用不同视角(如无人机、卫星和街景)以及模态(如语言和图像)之间的互补线索。为了解决这些挑战,我们提出了GeoBridge,这是一种基础模型,它可以在不同的视图之间进行双向匹配并支持从语言到图像的检索。超越传统的以卫星为中心的形式化方法,GeoBridge建立了一种新颖的语义锚机制,通过文本描述将多视角特征联系起来,从而实现稳健和灵活的位置定位。 为了支持这一任务,我们构建了GeoLoc,这是首个大规模、跨模态、多视图对齐的数据集,包含来自36个国家超过50,000对无人机、街景全景和卫星图像及其文本描述,确保地理和语义上的对齐。我们在多个任务上进行了广泛的评估。实验结果确认了GeoLoc预训练显著提高了GeoBridge的地理定位准确性,并促进了跨域泛化和跨模态知识转移。 数据集、源代码以及预训练模型可在[该网址](请将URL替换为实际链接)获取。
URL
https://arxiv.org/abs/2512.02697