S cubed Geo: Structure-Semantic Synergistic Learning for Cross-View Geo-Localization
cs.CV
Submitted: 2026-10-08
Updated: 2026-10-08
License: http://creativecommons.org/licenses/by/4.0/
The gist: Cross-view geo-localization (CVGL) aims to estimate geographic locations by matching images captured from different viewpoints, such as drone and satellite views.
Terminology
Abstract
Cross-view geo-localization (CVGL) aims to estimate geographic locations by matching images captured from different viewpoints, such as drone and satellite views. Existing methods mainly rely on visual representations, but often fail to jointly model fine-grained structural correspondences and semantic priors, making them prone to confusion between visually similar but semantically different regions, and thus limiting robustness under large viewpoint variations. To address these challenges, we propose S cubed Geo, a structure-semantic synergistic learning framework for cross-view matching. Specifically, we first introduce a Decoupled Query Pooling (DQP) module to extract a compact set of region-aware features from dense tokens, enabling explicit modeling of local structural patterns. We then design a query-level contrastive learning scheme with an optimal transport (OT)-based formulation to establish soft correspondences under cross-view spatial misalignment. Furthermore, we incorporate a Semantic Knowledge Distillation (SKD) strategy from a frozen CLIP teacher to transfer semantic priors and relational structures, thereby improving discrimination on hard negatives. By operating synergistically, the semantic priors provide robust contextual filtering, which guides the structural module to establish precise spatial alignments. Experiments on the University-1652 and SUES-200 datasets demonstrate that S cubed Geo consistently outperforms state-of-the-art approaches without increasing inference complexity, validating the effectiveness of jointly modeling structural and semantic information for CVGL.
Sources
- Distilling the Knowledge in a Neural Network
- GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Decoupled Weight Decay Regularization
- Representation Learning with Contrastive Predictive Coding
- DINOv2: Learning Robust Visual Features without Supervision
- DINOv3
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models