Pinpoint: Grounded Worldwide Image Geolocation via Cross-Source Retrieval and Reranking 文章

ArXiv CS.CV2026-06-04NEWSen作者: Nika Chuzhoy, Brian Hu, Amit A. Arora, Jae Ro, Sarthak S. Sahu

摘要

arXiv:2606.04133v1 Announce Type: new Abstract: Image geolocation aims to estimate where a photograph was taken from its visual content. At worldwide scale, this remains challenging because visual evidence is often ambiguous, diverse, and unevenly distributed. Prior work has typically treated geolocation of ordinary internet photos and street-view imagery as separate tasks, despite their complementary strengths: internet photos better match the appearance distribution of user-captured queries, while street-view imagery provides denser, geographically grounded coverage. We present Pinpoint, a retrieve-and-rerank architecture that combines both sources in a coarse-to-fine pipeline. A contrastive image-GPS embedder is trained on both user-uploaded Flickr photos and street-view imagery, learning a shared image-GPS embedding space that is used to retrieve candidate locations.

相关公司查看全部 (1)

F
FlickrCOMPANY

相关人物

暂无数据

相关技术

暂无数据