将陆地卫星影像转为高光谱图像，速度快且结果可解释。
Interpretable Landsat-to-Hyperspectral Dual Super-Resolution Without Large Matrix Inversion
- 用无大型矩阵求逆的算法实现空间与光谱双超分辨率。
- 重建精度提升，分类准确率从78.98%升至92.16%。
- 适合需要高精度遥感分析的研究者和应用团队。
当前硬件条件下无法直接获取全球高光谱图像（HSIs），但其在遥感中至关重要。更经济的方法是将全球陆地卫星-8/9多光谱图像（30米）转换为美国宇航局AVIRIS级高光谱图像（172波段）。该转换包含空间超分辨率（30米→15米）与高度病态的光谱超分辨率（7波段→172波段），统称为双超分辨率（DualSR）。现有光谱超分辨率方法主要针对仅含31个可见波段的CAVE级数据，不适用于涉及172个波段的AVIRIS级任务。为此，我们基于Woodbury W-Lemma与光谱连续性先验，定制了可解释的交替方向乘子法网络（ADMM-Net）。不同于传统生成式空间超分辨率，采用全色锐化策略恢复物理上合理的空间细节。然而，该策略仍导致大规模矩阵求逆（LMIs），即使使用W-Lemma也难以避免。我们通过设计免大矩阵求逆的近端梯度下降网络（PGD-Net），彻底解决此问题。最终提出的可解释网络PAINT在计算复杂度与重建性能上均有显著提升。不仅超越现有最佳表现，还将陆地卫星分类准确率从78.98%提升至92.16%，κ系数从76.06%升至90.98%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。