What question did this study set out to answer?

The aim is to improve the spatial and spectral quality of hyperspectral pansharpening by addressing global dependencies in cross-modal features.

May 4, 20260 citationsOpen Access

HPN-ICE: Information Cross Embedding for Hyperspectral Pansharpening

YJYan JinTiangong University

Key Points

The aim is to improve the spatial and spectral quality of hyperspectral pansharpening by addressing global dependencies in cross-modal features.
Developed a hyperspectral pansharpening network called HPN-ICE integrating global feature fusion and multi-directional feature enhancement modules.
Implemented feature embedding fusion for efficient cross-dependencies between hyperspectral and panchromatic images.
Utilized frequency-domain channel attention to enhance global spectral information.
HPN-ICE shows significant improvements over state-of-the-art methods in spatial quality metrics.
Achieved notable enhancements in spectral quality metrics, indicating better preservation of spectral information.
Extensive experiments on three datasets confirm the efficacy of the proposed method.

Abstract

Hyperspectral (HS) pansharpening aims to generate high-spatial-resolution hyperspectral (HRHS) images by fusing panchromatic (PAN) images with low-spatial-resolution hyperspectral (LRHS) images. However, many existing HS pansharpening methods fail to capture global dependencies between cross-modal features, leading to spectral and spatial distortions.To address this issue, we propose a hyperspectral pansharpening network based on information cross embedding (HPN-ICE). The model progressively fuses HS and PAN image features through two modules: the global feature fusion module (GFFM) and the multi-directional feature enhancement module (MFEM). In GFFM, a feature embedding fusion module (FEFM) is firstly designed based on the information cross embedding, which efficiently fuses spectral and spatial features by establishing cross dependencies between two modal features. Then, a frequency-domain channel attention module (FCAM) is constructed to enhance the global spectral information in the frequency domain. MFEM is constructed to enhance the local details of fused features in multi-dimensional directions. Extensive experiments conducted on three widely used datasets demonstrate that HPN-ICE achieves significant improvements in both spatial and spectral quality metrics over some state-of-the-art (SOTA) methods. The code will be released on GitHub.

Ask AI

Helpful

Bookmark

View Full Paper