2025
TerraMind: Large-Scale Generative Multimodality for Earth Observation
Johannes Jakubik, Felix Yang, Benedikt Blumenstiel, Erik Scheurer, Rocco Sedona, Stefano Maurogiovanni +10
ICCV 2025poster
We present TerraMind, the first any-to-any generative, multi-modal foundation model for Earth observation (EO). Unlike other multimodal models, TerraMind is pretrained on dual-scale representations combining both token-level and pixel-level data across modalities. On a token level, TerraMind encodes…