5 papers · 1 filter
UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
Yohann Perron, Guillaume Astruc, Nicolas Gonthier +2
Vision Transformers (ViT) dominate computer vision. However, their reliance on rigid patch projectors hinders transfer to Earth Observation (EO), where input modalities, scales, an…
The Global-Local loop: what is missing in bridging the gap between geospatial data from numerous communities?
Clément Mallet, Ana-Maria Raimond
We face a unprecedented amount of geospatial data, describing directly or indirectly the Earth Surface at multiple spatial, temporal, and semantic scales, and stemming from numerou…
AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities
Guillaume Astruc, Nicolas Gonthier, Clement Mallet +1
Geospatial models must adapt to the diversity of Earth observation data in terms of resolutions, scales, and modalities. However, existing approaches expect fixed input configurati…
The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generation
Yanis Benidir, Nicolas Gonthier, Clement Mallet
Bi-temporal change detection at scale based on Very High Resolution (VHR) images is crucial for Earth monitoring. This remains poorly addressed so far: methods either require large…
OmniSat: Self-Supervised Modality Fusion for Earth Observation
Guillaume Astruc, Nicolas Gonthier, Clement Mallet +1
The diversity and complementarity of sensors available for Earth Observations (EO) calls for developing bespoke self-supervised multimodal learning approaches. However, current mul…