An unsupervised HS-SISR framework trains a super-resolution network on synthetic abundance maps from a dead leaves model derived from the low-resolution input and known PSF, then reconstructs the enhanced hyperspectral image via unmixing.
Generative adversarial net- works for realistic synthesis of hyperspectral samples,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Synthetic Abundance Maps for Unsupervised Super-Resolution of Hyperspectral Remote Sensing Images
An unsupervised HS-SISR framework trains a super-resolution network on synthetic abundance maps from a dead leaves model derived from the low-resolution input and known PSF, then reconstructs the enhanced hyperspectral image via unmixing.