UniGeoCLIP: Unified Geospatial Contrastive Learning

Guillaume Astruc, Eduard Trulls, Jan Hosang, Loic Landrieu, Paul-Edouard Sarlin; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026, pp. 7847-7856

The growing availability of co-located geospatial data spanning aerial imagery, street-level views, elevation models, text, and geographic coordinates offers a unique opportunity for multimodal representation learning. We introduce UniGeoCLIP, a massively multimodal contrastive framework to jointly align five complementary geospatial modalities in a single unified embedding space. Unlike prior approaches that fuse modalities or rely on a central pivot representation, our method performs all-to-all contrastive alignment, enabling seamless comparison, retrieval, and reasoning across arbitrary combinations of modalities. We further propose a scaled latitude-longitude encoder that improves spatial representation by capturing multi-scale geographic structure. Extensive experiments across downstream geospatial tasks demonstrate that UniGeoCLIP consistently outperforms single-modality contrastive models and coordinate-only baselines, highlighting the benefits of holistic multi-modal geospatial alignment.