基于物理的无训练学习用于RGB引导的超分辨率单像素超光谱成像
Physics-Informed Untrained Learning for RGB-Guided Superresolution Single-Pixel Hyperspectral Imaging
AI总结：
本文提出一种基于物理的无训练框架，利用未训练的神经网络和RGB引导，实现超分辨率和超光谱重建，无需外部训练数据，实验表明其在重建精度和光谱保真度上优于现有方法。
摘要：
单像素成像（SPI）为超光谱获取提供了成本效益的途径，但在极低采样率下难以恢复高保真的空间和光谱细节，这是一个严重病态的逆问题。尽管深度学习显示出潜力，但现有数据驱动方法需要大规模预训练数据集，这在超光谱成像中往往不现实。为克服这一限制，我们提出了一种端到端的基于物理的框架，利用未训练的神经网络和RGB引导，实现超光谱重建和超分辨率，而无需任何外部训练数据。该框架包含三个物理基础阶段：（1）一种正则化最小二乘法结合RGB衍生的灰度先验（LS-RGP），通过利用跨模态结构相关性初始化解决方案；（2）一种未训练的超光谱恢复网络（UHRNet），通过测量一致性和混合正则化来细化重建；（3）一种基于Transformer的未训练超分辨率网络（USRNet），通过跨模态注意力机制提升空间分辨率，将高频细节从RGB引导中转移。在基准数据集上的广泛实验表明，我们的方法在重建精度和光谱保真度上显著优于现有最先进算法。此外，使用物理单像素成像系统进行的原理验证实验验证了框架的实用性，成功在仅6.25%的采样率下重建了一个144波段的超光谱数据立方体。所提出的方法因此为计算超光谱成像提供了一种稳健且数据高效的解决方案。
英文摘要：
Single-pixel imaging (SPI) offers a cost-effective route to hyperspectral acquisition but struggles to recover high-fidelity spatial and spectral details under extremely low sampling rates, a severely ill-posed inverse problem. While deep learning has shown potential, existing data-driven methods demand large-scale pretraining datasets that are often impractical in hyperspectral imaging. To overcome this limitation, we propose an end-to-end physics-informed framework that leverages untrained neural networks and RGB guidance for joint hyperspectral reconstruction and super-resolution without any external training data. The framework comprises three physically grounded stages: (1) a Regularized Least-Squares method with RGB-derived Grayscale Priors (LS-RGP) that initializes the solution by exploiting cross-modal structural correlations; (2) an Untrained Hyperspectral Recovery Network (UHRNet) that refines the reconstruction through measurement consistency and hybrid regularization; and (3) a Transformer-based Untrained Super-Resolution Network (USRNet) that upsamples the spatial resolution via cross-modal attention, transferring high-frequency details from the RGB guide. Extensive experiments on benchmark datasets demonstrate that our approach significantly surpasses state-of-the-art algorithms in both reconstruction accuracy and spectral fidelity. Moreover, a proof-of-concept experiment using a physical single-pixel imaging system validates the framework's practical applicability, successfully reconstructing a 144-band hyperspectral data cube at a mere 6.25% sampling rate. The proposed method thus provides a robust, data-efficient solution for computational hyperspectral imaging.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
