Single Hyperspectral Image Super-Resolution Using An Efficient Transformer Network

Haijun Wang

doi:10.1016/j.inffus.2026.104429

Single Hyperspectral Image Super-Resolution Using An Efficient Transformer Network

2026-04-26

0

PRE

AI

DOI：10.1016/j.inffus.2026.104429

Original

Original request for help

Save

Abstract

En 中文

• We propose ETNet, an efficient Transformer for unified SHSI-SR modeling. • Our SSM jointly captures global spatial context and inter-band correlations. • We leverage SCC to formulate linear-complexity kernelized spatial attention. • A streamlined GFFN and spectral attention pathway enhance feature integration. • ETNet achieves state-of-the-art accuracy and visual realism on benchmarks.

Keywords:

ETNet

Transformer

SHSI-SR

spatial context

spectral attention

Single Hyperspectral Image Super-Resolution Using An Efficient Transformer Network

Abstract

Journal

Organization