LRDUN：面向高效光谱压缩成像的低秩深度展开网络
LRDUN: A Low-Rank Deep Unfolding Network for Efficient Spectral Compressive Imaging
把低秩分解显式嵌入感知模型，使展开网络的每一阶段只在低维光谱基/子空间图像上做近端梯度更新，从而缓解 2D 残差映射回 3D 高光谱的病态性并降低计算量；这套「低秩感知模型 + 展开优化」思路可直接迁移到其他高维逆问题（视频快照压缩成像、多光谱去马赛克）。
原文依据 we propose two novel imaging models corresponding to the spectral basis and subspace image by explicitly integrating low-rank (LR) decomposition with the sensing model
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论深度展开网络（DUN）已取得显著成功，并成为光谱压缩成像（SCI）重建的主流范式。现有 DUN 均源自全高光谱图像（HSI）成像模型，其中每个阶段直接在高维 HSI 上运算，依据单幅二维编码测量对整幅数据立方体进行细化。然而，该范式导致计算冗余，并且受制于将二维残差映射回 HSI 三维空间的病态性。本文通过将低秩（LR）分解与感知模型显式结合，提出了分别对应光谱基与子空间图像的两种新成像模型。与恢复完整 HSI 相比，估计这些紧凑的低维分量可显著缓解病态性。基于这些新模型，我们构建了低秩深度展开网络（LRDUN），在展开的近端梯度下降（PGD）框架内联合求解上述两个子问题。此外，我们引入了广义特征展开机制（GFUM），将数据保真项中的物理秩与先验模块中的特征维度解耦，从而增强网络的表征能力与灵活性。在仿真与真实数据集上的大量实验表明，所提出的 LRDUN 在显著降低计算成本的同时达到了最优（SOTA）的重建质量。代码见 https://github.com/huang-he99/LRDUN。
英文原文摘要 1507 字符
Deep unfolding networks (DUNs) have achieved remarkable success and become the mainstream paradigm for spectral compressive imaging (SCI) reconstruction. Existing DUNs are derived from full-HSI imaging models, where each stage operates directly on the high-dimensional HSI, refining the entire data cube based on the single 2D coded measurement. However, this paradigm leads to computational redundancy and suffers from the ill-posed nature of mapping 2D residuals back to 3D space of HSI. In this paper, we propose two novel imaging models corresponding to the spectral basis and subspace image by explicitly integrating low-rank (LR) decomposition with the sensing model. Compared to recovering the full HSI, estimating these compact low-dimensional components significantly mitigates the ill-posedness. Building upon these novel models, we develop the Low-Rank Deep Unfolding Network (LRDUN), which jointly solves the two subproblems within an unfolded proximal gradient descent (PGD) framework. Furthermore, we introduce a Generalized Feature Unfolding Mechanism (GFUM) that decouples the physical rank in the data-fidelity term from the feature dimensionality in the prior module, enhancing the representational capacity and flexibility of the network. Extensive experiments on simulated and real datasets demonstrate that the proposed LRDUN achieves state-of-the-art (SOTA) reconstruction quality with significantly reduced computational cost. Code is available at https://github.com/huang-he99/LRDUN.