Cross-view geo-localization between drone and satellite images is severely challenged by rapid weather variations, which induce appearance shifts, occlusions, and texture degradation. Inspired by human foveal attention, we propose the Fovea Attention Network (FANet), a robust dual-branch framework comprising: (1) The Weather-Adaptive Global Branch (WAGB) that explicitly injects weather cues (e.g., 'rain/snow') into the feature space via a style-modulation encoder, then captures large-scale structural consistency through a Learnable Region Reassembly (LRR) mechanism; (2) The Local Semantic Attention Branch (LSAB) that leverages a pretrained segmentation model to generate high-confidence masks, distilling discriminative features from salient regions. An adaptive fusion strategy module fuses global context with fine-grained semantic cues. We further adopt multi-weather adaptive training, treating weather types as related tasks with shared parameters to reduce cross-weather confounding. Extensive experiments on University-1652, SUES-200, and CVUSA show FANet achieves competitive Recall@1 across all conditions, attaining the highest overall mean with the lowest variance. Notably, it improves Recall@1 by 6.79% under severe low-illumination ('dark') conditions, demonstrating robustness and stability.
Wen et al. (Thu,) studied this question.