MRGeo: Robust Cross-View Geo-Localization of Corrupted Images via Spatial and Channel Feature Enhancement

2026-03-12

AI Summary

Existing cross-view geolocalization methods suffer significant performance degradation under real-world image degradations such as blur and adverse weather conditions. To address this robustness challenge, this work proposes MRGeo, the first approach to systematically tackle these issues by enhancing feature quality through a spatial-channel enhancement module and introducing a region-level geometric alignment mechanism that effectively fuses local and global information. MRGeo further models multi-granularity channel dependencies and incorporates dynamic gating to achieve spatially adaptive representations. Evaluated on three robustness benchmarks, MRGeo achieves an average R@1 improvement of 2.92% and substantially outperforms state-of-the-art methods in cross-region evaluations.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Multi-instance/Multi-view Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Cross-view geo-localization (CVGL) aims to accurately localize street-view images through retrieval of corresponding geo-tagged satellite images. While prior works have achieved nearly perfect performance on certain standard datasets, their robustness in real-world corrupted environments remains under-explored. This oversight causes severe performance degradation or failure when images are affected by corruption such as blur or weather, significantly limiting practical deployment. To address this critical gap, we introduce MRGeo, the first systematic method designed for robust CVGL under corruption. MRGeo employs a hierarchical defense strategy that enhances the intrinsic quality of features and then enforces a robust geometric prior. Its core is the Spatial-Channel Enhancement Block, which contains: (1) a Spatial Adaptive Representation Module that models global and local features in parallel and uses a dynamic gating mechanism to arbitrate their fusion based on feature reliability; and (2) a Channel Calibration Module that performs compensatory adjustments by modeling multi-granularity channel dependencies to counteract information loss. To prevent spatial misalignment under severe corruption, a Region-level Geometric Alignment Module imposes a geometric structure on the final descriptors, ensuring coarse-grained consistency. Comprehensive experiments on both robustness benchmark and standard datasets demonstrate that MRGeo not only achieves an average R@1 improvement of 2.92\% across three comprehensive robustness benchmarks (CVUSA-C-ALL, CVACT\_val-C-ALL, and CVACT\_test-C-ALL) but also establishes superior performance in cross-area evaluation, thereby demonstrating its robustness and generalization capability.

Problem

• cross-view geo-localization
• image corruption
• robustness
• blur
• weather

Innovation

• cross-view geo-localization
• robustness to corruption
• spatial-channel enhancement
• geometric alignment
• feature calibration