CVGL: Causal Learning and Geometric Topology

TL;DR

This paper introduces CLGT, a novel framework for cross-view geo-localization that combines causal feature extraction, geometric topology fusion, and adaptive pooling to improve robustness and accuracy in complex real-world scenarios.

Contribution

The paper proposes a new CLGT framework integrating causal learning and geometric topology to address viewpoint variations and confounding factors in CVGL.

Findings

Achieves state-of-the-art performance on CVUSA and CVACT datasets.

Demonstrates robustness under real-world corruptions.

Outperforms existing methods in challenging scenarios.

Abstract

Cross-view geo-localization (CVGL) aims to estimate the geographic location of a street image by matching it with a corresponding aerial image. This is critical for autonomous navigation and mapping in complex real-world scenarios. However, the task remains challenging due to significant viewpoint differences and the influence of confounding factors. To tackle these issues, we propose the Causal Learning and Geometric Topology (CLGT) framework, which integrates two key components: a Causal Feature Extractor (CFE) that mitigates the influence of confounding factors by leveraging causal intervention to encourage the model to focus on stable, task-relevant semantics; and a Geometric Topology Fusion (GT Fusion) module that injects Bird's Eye View (BEV) road topology into street features to alleviate cross-view inconsistencies caused by extreme perspective changes. Additionally, we introduce a Data-Adaptive Pooling (DA Pooling) module to enhance the representation of semantically rich regions. Extensive experiments on CVUSA, CVACT, and their robustness-enhanced variants (CVUSA-C-ALL and CVACT-C-ALL) demonstrate that CLGT achieves state-of-the-art performance, particularly under challenging real-world corruptions. Our codes are available at https://github.com/oyss-szu/CLGT.