2026
D3A-Net: A Deformable 3-D Attention Network for Hyperspectral Unmixing
Hyperspectral unmixing (HU) aims to decompose mixed pixels into endmember spectra and corresponding abundance maps under physically interpretable constraints. Despite recent progress in convolutional neural network (CNN)- and Transformer-based approaches, most existing methods still rely on rigid sampling grids or proc...
Fang-Qiang Kong, Hao-Cheng Yang, Zhi-Bo Wu et al.
· IEEE Transactions on Geoscie... · 0 citations