GeoStore: Finding Small Storefronts in Large Scenes -- A Fine-Grained POI Localization Benchmark with Global-to-Local Asymmetric Matching
Read the original on arXiv Computer Vision →GeoStore is a new benchmark for fine‑grained point‑of‑interest (POI) localization that matches close‑up storefront photos against large geo‑tagged street‑view images, a task distinct from traditional visual place recognition. The paper shows that global‑descriptor methods designed for symmetric matching perform poorly on this asymmetric problem, and introduces GLAM, a Global‑to‑Local Asymmetric Matching approach that combines a global retrieval anchor with a lightweight local re‑ranking using pooled region tokens. GLAM achieves higher Recall@1/5/10 and mAP than strong baselines while using far fewer re‑ranking features and significantly lower per‑pair matching cost.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.