基于对抗展开与数据驱动光谱正则化的光谱超分辨率：从多光谱卫星数据到 NASA 高光谱图像
Spectral Super-Resolution via Adversarial Unfolding and Data-Driven Spectrum Regularization: From Multispectral Satellite Data to NASA Hyperspectral Image
把深度展开网络与数据驱动先验网络（PriorNet）结合，并在展开架构中嵌入对抗判别器，使判别器在训练与测试阶段都参与重建；这一「展开对抗学习」思路可迁移到其他病态逆问题（如去噪、去模糊、超分辨率）中，用轻量先验网络替代隐式深度先验以大幅降低 MACs 与参数量。
原文依据 we formulate a novel deep unfolding framework regularized by a data-driven spectrum prior from PriorNet
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论欧洲空间局的 Sentinel-2 卫星为遥感（RS）应用提供全球多光谱覆盖。然而，其有限的光谱分辨率（12 个波段）与不统一的空问分辨率（60/20/10 米）限制了其实用性。相比之下，高光谱-空间分辨率传感器（如 NASA 的 AVIRIS-NG）出于实际考虑仅覆盖美洲区域。这引出一个根本性问题：“能否通过将 Sentinel-2 数据重建为 NASA 高光谱图像来实现全球高光谱覆盖？”本研究旨在实现从 12 波段到 186 波段的光谱超分辨率，并将 Sentinel-2 数据的空间分辨率统一到 5 米。为实现可靠且高效的重建，我们构建了一种新颖的深度展开框架，该框架由来自 PriorNet 的数据驱动光谱先验进行正则化，而非像传统深度展开那样依赖隐式深度先验。此外，我们在展开架构中引入了对抗项，使判别器在训练和测试阶段都能引导重建；我们将这一新概念称为展开对抗学习（UAL）。实验表明，我们的 UALNet 在 PSNR、SSIM 和 SAM 上优于次优的 Transformer，同时仅需 15% 的 MACs 和少 20 倍的参数量。相关代码已公开于 https://github.com/IHCLab/UALNet。
英文原文摘要 1383 字符
The European Space Agency's Sentinel-2 satellite provides global multispectral coverage for remote sensing (RS) applications. However, limited spectral resolution (12 bands) and non-unified spatial resolution (60/20/10 m) restrict their practicality. In contrast, the high spectral-spatial resolution sensor (e.g., NASA's AVIRIS-NG) covers only the American region due to practical considerations. This raises a fundamental question: "Can a global hyperspectral coverage be achieved by reconstructing Sentinel-2 data to NASA hyperspectral images?" This study aims to achieve spectral super-resolution from 12-to-186 and unify the spatial resolution of Sentinel-2 data to 5 m. To enable a reliable and efficient reconstruction, we formulate a novel deep unfolding framework regularized by a data-driven spectrum prior from PriorNet, instead of relying on implicit deep priors as conventional deep unfolding does. Moreover, an adversarial term is integrated into the unfolded architecture, enabling the discriminator to guide the reconstruction in both the training and testing phases; we term this novel concept unfolding adversarial learning (UAL). Experiments show that our UALNet outperforms the next-best Transformer in PSNR, SSIM, and SAM, while requiring only 15% MACs and 20 times fewer parameters. The associated code is publicly available at https://github.com/IHCLab/UALNet.