Just Zoom In: Cross-View Geo-Localization via Autoregressive Zooming

2026-03-26

AI Summary

This work addresses the ambiguity in cross-view geolocalization caused by mismatched coverage between street-level and overhead views, as well as the absence of explicit geometric modeling. To this end, the authors propose an autoregressive, zoom-based sequential decision framework that progressively refines the target location from coarse to fine on city-scale high-resolution satellite imagery. Departing from conventional contrastive learning and hard negative mining, the method enables explicit spatial reasoning through multi-scale map zooming. Additionally, a new benchmark dataset is introduced to better reflect real-world scenarios. Experimental results demonstrate state-of-the-art performance, with Recall@1 improvements of 5.5% within 50 meters and 9.6% within 100 meters on the proposed benchmark.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Search and Optimization: Learning to Search
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Cross-view geo-localization (CVGL) estimates a camera's location by matching a street-view image to geo-referenced overhead imagery, enabling GPS-denied localization and navigation. Existing methods almost universally formulate CVGL as an image-retrieval problem in a contrastively trained embedding space. This ties performance to large batches and hard negative mining, and it ignores both the geometric structure of maps and the coverage mismatch between street-view and overhead imagery. In particular, salient landmarks visible from the street view can fall outside a fixed satellite crop, making retrieval targets ambiguous and limiting explicit spatial inference over the map. We propose Just Zoom In, an alternative formulation that performs CVGL via autoregressive zooming over a city-scale overhead map. Starting from a coarse satellite view, the model takes a short sequence of zoom-in decisions to select a terminal satellite cell at a target resolution, without contrastive losses or hard negative mining. We further introduce a realistic benchmark with crowd-sourced street views and high-resolution satellite imagery that reflects real capture conditions. On this benchmark, Just Zoom In achieves state-of-the-art performance, improving Recall@1 within 50 m by 5.5% and Recall@1 within 100 m by 9.6% over the strongest contrastive-retrieval baseline. These results demonstrate the effectiveness of sequential coarse-to-fine spatial reasoning for cross-view geo-localization.

Problem

• cross-view geo-localization
• coverage mismatch
• spatial inference
• landmark visibility
• overhead imagery

Innovation

• autoregressive zooming
• cross-view geo-localization
• sequential spatial reasoning
• satellite imagery
• non-contrastive localization