SeqLoc: Beyond the Single Frame for Cross-View Geo-Localization in Feature-Sparse Scenes

2026-08-07

AI Summary

This work addresses the significant performance degradation of existing OpenStreetMap-based cross-view geolocalization methods in feature-sparse environments, such as rural roads. To overcome this limitation, the authors propose SeqLoc, an online test-time sequential aggregation mechanism that recursively maintains a log-confidence volume to fuse information from consecutive panoramic images and map data for robust localization. The approach introduces three key innovations: entropy-modulated uncertainty modeling, map-guided relocalization, and peak-anchored smoothing, which collectively recover suppressed true poses and achieve sub-grid accuracy. Experimental results demonstrate that SeqLoc improves both positional and orientation recall by over 50% on the CV-FSS and CV-RHO benchmarks, substantially outperforming single-frame baselines.

Abstract

Cross-View Geo-Localization (CVGL) with OpenStreetMap (OSM) performs well in structure-rich urban environments but collapses in feature-sparse scenes such as rural roads. To study this failure mode, in this work, we introduce CV-FSS, a benchmark that pairs sequential panoramas from five rural regions with aligned OSM maps, on which single-frame methods degrade drastically. We then propose SeqLoc, an online test-time sequence aggregation mechanism that recursively maintains a log-belief volume with three key components: (1) Entropy-Tempered Uncertainty (ETU) tempers each incoming pose likelihood volume by its normalized entropy; (2) Map-Guided Relocalization (MGR) mixes a map-shaped recovery distribution into the belief so that a suppressed true pose can recover; (3) Peak-Anchored Smoothing (PAS) derives the final pose at sub-grid precision. Extensive experiments on CV-FSS and CV-RHO demonstrate that SeqLoc outperforms single-frame localization by a large margin, improving both position and orientation recall by over 50%. The benchmark and source code will be made publicly available.

Problem

• Cross-View Geo-Localization
• feature-sparse scenes
• sequential localization
• rural environments
• OSM-based localization

Innovation

• SeqLoc
• Cross-View Geo-Localization
• Feature-Sparse Scenes
• Sequence Aggregation
• Map-Guided Relocalization