3 papers
cs.CV2026
GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI
Naomi Simumba, Nils Lehmann, Paolo Fraccaro +9
Geospatial Foundation Models (GeoFMs) are transforming Earth Observation (EO), but evaluation lacks standardized protocols. GEO-Bench-2 addresses this with a comprehensive framewor…
cs.CV2025
Toward task-driven satellite image super-resolution
Maciej Ziaja, Pawel Kowaleczko, Daniel Kostrzewa +2
Super-resolution is aimed at reconstructing high-resolution images from low-resolution observations. State-of-the-art approaches underpinned with deep learning allow for obtaining…
cs.CV2024
Unlocking the Use of Raw Multispectral Earth Observation Imagery for Onboard Artificial Intelligence
Gabriele Meoni, Roberto Del Prete, Federico Serva +3
Nowadays, there is growing interest in applying Artificial Intelligence (AI) on board Earth Observation (EO) satellites for time-critical applications, such as natural disaster res…