DualGeo通过双视角融合与地理聚类，提升全球图像定位精度。
DualGeo: A Dual-View Framework for Worldwide Image Geo-localization
- 融合图像与语义分割特征，用双向注意力建模地理表征。
- 在IM2GPS等数据集上，街级定位准确率提升最高达16.58%。
- 适合需要高精度地理定位的遥感、导航与地图应用。
全球图像地理定位旨在推断任意地球位置拍摄图像的地理坐标，覆盖街巷、城市、区域、国家乃至大陆尺度。现有方法依赖对环境变化（如光照、季节、天气）敏感的视觉特征，且缺乏有效后处理过滤异常候选，限制了定位精度。为此，我们提出DualGeo，一种两阶段全球图像地理定位框架。首先，通过双向交叉注意力融合图像与语义分割特征，建立地理表征基础；再通过双视角对比学习将融合特征与经纬度对齐，构建全局检索数据库。其次，通过地理聚类重排检索候选，并输入大模型进行最终坐标预测。在IM2GPS、IM2GPS3k和YFCC4k数据集上的实验表明，DualGeo优于当前最优方法，街级（<1 km）定位准确率提升3.6%-16.58%，城市级（<25 km）提升1.29%-8.77%。代码与数据集已开源：https://github.com/CJ310177/DualGeo。
原文摘要 · Abstract (English)
Worldwide image geo-localization aims to infer the geographic location of an image captured anywhere on Earth, spanning street, city, regional, national, and continental scales. Existing methods rely on visual features that are sensitive to environmental variations (e.g., lighting, season, and weather) and lack effective post-processing to filter outlier candidates, limiting localization accuracy. To address these limitations, we propose DualGeo, a two-stage framework for worldwide image geo-localization. First, it establishes a geo-representational foundation by fusing image and semantic segmentation features via bidirectional cross-attention. The fused features are then aligned with GPS coordinates through dual-view contrastive learning to build a global retrieval database. Second, it performs geo-cognitive refinement by re-ranking retrieved candidates using geographic clustering. It then feeds them into large multimodal models (LMMs) for final coordinate prediction. Experiments on IM2GPS, IM2GPS3k, and YFCC4k show that DualGeo outperforms state-of-the-art methods, improving street-level (<1 km) and city-level (<25 km) localization accuracy by 3.6%-16.58% and 1.29%-8.77%, respectively. Our code and datasets are available : https://github.com/CJ310177/DualGeo.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。