Self-supervised pre-training with geospatially-aware masked autoencoders reconstructs 3D cloud profiles from geostationary satellite imagery more accurately than a U-Net baseline.
The EarthCARE mission–science and system overview
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
3D Cloud reconstruction through geospatially-aware Masked Autoencoders
Self-supervised pre-training with geospatially-aware masked autoencoders reconstructs 3D cloud profiles from geostationary satellite imagery more accurately than a U-Net baseline.