SpectraMorph is a physics-guided self-supervised framework for hyperspectral super-resolution that enforces an unmixing bottleneck to extract endmembers from low-resolution HSI and predict abundance-like maps from MSI for linear mixing reconstruction.
FusFormer: A transformer-based fusion network for hyperspectral image super-resolution
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SpectraMorph: Structured Latent Learning for Self-Supervised Hyperspectral Super-Resolution
SpectraMorph is a physics-guided self-supervised framework for hyperspectral super-resolution that enforces an unmixing bottleneck to extract endmembers from low-resolution HSI and predict abundance-like maps from MSI for linear mixing reconstruction.