GeoSURGE：基于分层地理嵌入语义融合的地理定位
GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings
把地理坐标建模为分层可学习嵌入、并用潜变量交叉注意力把语义分割特征融进外观特征，这套「低维坐标→分布式多尺度嵌入」的对齐思路可迁移到其他需要回归连续空间量（如相机位姿、深度、BEV 位置）的视觉任务。
原文依据 we introduce a semantic fusion module that efficiently integrates appearance features with semantic segmentation through latent cross-attention
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论全球视觉地理定位旨在仅利用图像的视觉内容确定该图像在地球上任意位置的地理坐标。尽管近期取得了进展，但由于地理坐标本身固有的低维特性，学习具有表达力的地理空间表征仍然具有挑战性。我们将全局地理定位建模为将查询图像的视觉表征与学习到的地理表征进行对齐。我们的方法显式地将世界建模为分层的学习地理嵌入，从而实现对地理空间的分布式多尺度表征。此外，我们引入一个语义融合模块，通过潜变量交叉注意力高效地将外观特征与语义分割相融合，从而产生更鲁棒、更利于定位的视觉表征。在五个广泛使用的地理定位基准上的实验表明，我们的方法在报告的 25 项指标中有 22 项取得了新的最优结果。消融研究表明，这些提升主要来自所提出的地理表征与语义融合机制。
英文原文摘要 1126 字符
Worldwide visual geo-localization aims to determine the geographic location of an image anywhere on Earth using only its visual content. Despite recent progress, learning expressive representations of geographic space remains challenging due to the inherently low-dimensional nature of geographic coordinates. We formulate global geo-localization as aligning the visual representation of a query image with a learned geographic representation. Our approach explicitly models the world as a hierarchy of learned geographic embeddings, enabling a distributed and multi-scale representation of geographic space. In addition, we introduce a semantic fusion module that efficiently integrates appearance features with semantic segmentation through latent cross-attention, producing a more robust visual representation for localization. Experiments on five widely used geo-localization benchmarks demonstrate that our method achieves new state-of-the-art results on 22 of 25 reported metrics. Ablation studies show that these improvements are primarily driven by the proposed geographic representation and semantic fusion mechanism.