Multi-weather Cross-view Geo-localization Using Denoising Diffusion Models
This addresses geo-localization challenges for drones or autonomous systems in varying weather, but it is incremental as it builds on existing methods with a novel hybrid approach.
The paper tackles cross-view geo-localization in GNSS-denied environments by matching drone-view images with satellite-view images, introducing MCGF to dynamically adapt to unseen extreme weather conditions, achieving competitive results on the University160k-WX dataset.
Cross-view geo-localization in GNSS-denied environments aims to determine an unknown location by matching drone-view images with the correct geo-tagged satellite-view images from a large gallery. Recent research shows that learning discriminative image representations under specific weather conditions can significantly enhance performance. However, the frequent occurrence of unseen extreme weather conditions hinders progress. This paper introduces MCGF, a Multi-weather Cross-view Geo-localization Framework designed to dynamically adapt to unseen weather conditions. MCGF establishes a joint optimization between image restoration and geo-localization using denoising diffusion models. For image restoration, MCGF incorporates a shared encoder and a lightweight restoration module to help the backbone eliminate weather-specific information. For geo-localization, MCGF uses EVA-02 as a backbone for feature extraction, with cross-entropy loss for training and cosine distance for testing. Extensive experiments on University160k-WX demonstrate that MCGF achieves competitive results for geo-localization in varying weather conditions.