AI 中文总结
该研究针对Landsat转AVIRIS级HSI的双超分辨率任务，提出无大型矩阵求逆的可解释PAINT网络，提升了重建性能与Landsat分类精度。
AI 中文摘要
鉴于当前硬件设施和有限资源，直接获取全球高光谱图像（HSI）不可行，但全球高光谱监测对遥感应用至关重要。一种更经济的方法是可解释地将全球Landsat-8/9多光谱图像转换为NASA的AVIRIS级HSI。该转换涉及空间超分辨率（SpaSR，30米到15米）和高度不适定的光谱超分辨率（SpeSR，7波段到172波段），两者合称为双超分辨率（DualSR），其SpaSR与SpeSR之间的对偶关系近期已被确立。现有SpeSR方法大多设计用于重建仅含31个可见波段的CAVE级HSI，不适用于涉及172个可见、近红外和短波红外波段的AVIRIS级任务。这促使我们定制一种可解释的交替方向乘子法网络（ADMM-Net），使用Woodbury W引理和光谱连续性先验。与传统生成式SpaSR不同，我们采用全色锐化策略以恢复基于物理的空间细节，但该策略会引发非常大的矩阵求逆（LMI），即使应用W引理后，其维度仍与像素数量成正比。我们通过设计无LMI的近端梯度下降网络（PGD-Net）解决此问题，因此，所提出的PGD-ADMM可解释网络（PAINT）在计算复杂度和重建性能上均实现显著提升。除达到超越现有技术的重建性能外，PAINT还将Landsat分类的准确率从78.98%、kappa系数从76.06%提升至92.16%的准确率和90.98%的kappa系数。
英文摘要
Direct acquisition of global hyperspectral images (HSIs) is infeasible given contemporary hardware facilities and limited resources, while global hyperspectral monitoring is critical for remote sensing applications. A more economical approach is to interpretably convert global Landsat-8/9 multispectral images into NASA's AVIRIS-level HSIs. This conversion involves both spatial super-resolution (SpaSR, 30-m to 15-m) and the highly ill-posed spectral super-resolution (SpeSR, 7-band to 172-band), collectively referred to as dual super-resolution (DualSR), whose duality between SpaSR and SpeSR has recently been established. Existing SpeSR methods, mostly designed to reconstruct CAVE-level HSIs with only 31 visible bands, are not applicable to the AVIRIS-level task involving 172 visible, near-infrared, and shortwave-infrared bands. This motivates us to customize an interpretable alternating direction method of multipliers network (ADMM-Net) using the Woodbury W-Lemma and a spectral continuity prior. Unlike conventional generative SpaSR, we employ a panchromatic sharpening strategy to recover physically grounded spatial details. However, this strategy induces very large matrix inversions (LMIs), with dimensionality proportional to the number of pixels, even after applying the W-Lemma. We resolve this issue by designing an LMI-free proximal gradient descent network (PGD-Net). Consequently, the proposed PGD-ADMM interpretable network (PAINT) achieves substantial improvements in both computational complexity and reconstruction performance. Beyond state-of-the-art reconstruction performance, PAINT improves Landsat classification from 78.98% accuracy and 76.06% kappa to 92.16% accuracy and 90.98% kappa.
Comments17 pages; accepted for publication in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS). Source code: https://github.com/IHCLab/PAINT
