A geometry-guided, unfolded back-projection network with multi-head self-attention sharpens Sentinel-2's 20m bands to 10m using a cluster-learned guiding image, beating existing fusion methods by about 1 dB PSNR.
, author Huang, B
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Super-Resolution of Sentinel-2 Images Using a Geometry-Guided Back-Projection Network with Self-Attention
A geometry-guided, unfolded back-projection network with multi-head self-attention sharpens Sentinel-2's 20m bands to 10m using a cluster-learned guiding image, beating existing fusion methods by about 1 dB PSNR.