Spaces:
Running
title: README
emoji: π
colorFrom: purple
colorTo: red
sdk: static
pinned: false
IBM and ESA π Advancing Geospatial AI with TerraMind & MS-CLIP
IBM and the European Space Agency (ESA) Ξ¦-lab introduce TerraMind, the first multimodal, any-to-any generative foundation model for Earth Observation. TerraMind reaches new SOTA results on downstream tasks and introduces the "Thinking-in-Modalities" approach to handle missing modalities. The model was pre-trained in partnership with JΓΌlich Supercomputing Centre (Forschungszentrum JΓΌlich) and supported by the FAST-EO project.
π TerraMind has been accepted at ICCV 2025
Weβre honored to present our work at one of the most prestigious conferences in computer vision. Stay tuned for more details!
π MS-CLIP has been accepted at ECML 2025
Weβre honored to present our work at one of the most prestigious conferences on machine learning. Stay tuned for more details!
π TerraMesh has been accepted at CVPR EarthVision 2025
Weβre honored to present our work at one of the most well-known workshops for Earth observation. Stay tuned for more details!
π€ Open Source
The FAST-EO partners and ESA Ξ¦-lab are committed to Open Source, sharing knowledge, and driving innovation for the geospatial domain.
π Papers and Resources
Explore the technical paper detailing TerraMind's architecture and applications here. Details on MS-CLIP can be found here.
π Upcoming Models and Datasets
Stay tuned for our upcoming model and dataset releases like TerraMesh.
π Challenge
Already working with TerraMind? Submit your use case to the TerraMind Blue-Sky Challenge, a bi-monthly award spotlighting the boldest, most imaginative ways using TerraMind.
Explore our models, datasets, and papers, and join our discussions to shape the future of geospatial AI!