Beyond Paired Data: Self-Supervised UAV Geo-Localization from Reference Imagery Alone
This addresses the costly data acquisition issue for UAV autonomy in GNSS-denied environments, though it is incremental as it builds on existing matching approaches.
The paper tackles the problem of UAV geo-localization without paired UAV-satellite training data by learning from satellite images alone using a novel augmentation strategy, achieving competitive performance on a new real-world dataset.
Image-based localization in GNSS-denied environments is critical for UAV autonomy. Existing state-of-the-art approaches rely on matching UAV images to geo-referenced satellite images; however, they typically require large-scale, paired UAV-satellite datasets for training. Such data are costly to acquire and often unavailable, limiting their applicability. To address this challenge, we adopt a training paradigm that removes the need for UAV imagery during training by learning directly from satellite-view reference images. This is achieved through a dedicated augmentation strategy that simulates the visual domain shift between satellite and real-world UAV views. We introduce CAEVL, an efficient model designed to exploit this paradigm, and validate it on ViLD, a new and challenging dataset of real-world UAV images that we release to the community. Our method achieves competitive performance compared to approaches trained with paired data, demonstrating its effectiveness and strong generalization capabilities.