metadata
title: README
emoji: π
colorFrom: blue
colorTo: green
sdk: static
pinned: false
FAST-EO π Foundation Models for Earth Observation
FAST-EO is a European project funded by ESA, focused on developing open-source multimodal foundation models for Earth Observation. Our models are designed to handle multispectral and mulitmodal data, enabling new capabilities in geospatial AI. Find more information on our webiste: https://www.fast-eo.eu.
π§ Featured Models
- TerraMind: A generative, any-to-any multimodal foundation model for EO, co-developed with ESA Ξ¦-lab.
- MS-CLIP: A contrastive vision language model for multispectral EO data.
π Publications
- TerraMind β ICCV 2025
- MS-CLIP β ECML 2025
- TerraMesh dataset β CVPR EarthVision 2025
- SmallMinesDS dataset β IEEE Geoscience and Remote Sensing Letters
- HyBiomass dataset β IEEE Geoscience and Remote Sensing Letters
- HYPERVIEW dataset β IEEE Geoscience and Remote Sensing Magazine
π€ Partners
FAST-EO is funded by ESA and supported by a consortium of leading organizations:
- German Aerospace Center (DLR)
- ESA Ξ¦-lab
- IBM Research
- Forschungszentrum JΓΌlich
- KP Labs
π Open Collaboration
We are committed to open science, transparent benchmarking, and community-driven innovation. Explore our models, datasets, and tools β and help shape the future of geospatial AI.