A U-Net with channel attention and angle-conditioned normalization retrieves cloud optical thickness from two-band simulated radiance with lower MSE than single-angle deep models and IPA.
Dataset: Satellites capture cloud radiance observations from real clouds at specific solar zenith angles (SZAs) and view zenith angles (VZAs)
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
-
Cloud Optical Thickness Retrievals Using Angle Invariant Attention Based Deep Learning Models
A U-Net with channel attention and angle-conditioned normalization retrieves cloud optical thickness from two-band simulated radiance with lower MSE than single-angle deep models and IPA.