Fusion of hyperspectral image (HSI) and multispectral image (MSI) is a prevalent scheme to generate a HSI with enhanced spatial resolution. Current methods often fail to sufficiently leverage the effective spectral and spatial priors existing in the observed HSI and MSI to further enhance the fusion performance. To address this limitation, this paper proposes a novel HSI-MSI fusion approach, which integrates Sparse and Low Rank with a CNN denoiser (SLRCNN) while considering spectral dictionary optimization. Firstly, an initialized spectral dictionary is derived from the HSI. Next, the spatial coefficients optimization model is established by incorporating the sparse prior, local low-rank prior, and plugged image prior simultaneously, where the l1 norm is imposed to promote the sparse prior, and the super-pixel segmentation strategy is conducted on the MSI to impose the local low-rank prior while a well-trained CNN denoiser is plugged in to enforce the image prior. Then, the spectral dictionary optimization model is constructed to refine the initial spectral dictionary, capturing more detailed spectral characteristics to further improve the fusion results. Finally, the optimization process involves applying the split-augmented Lagrangian shrinkage method and the alternating direction method of multipliers. Experimental results on simulated and real datasets, namely the Pavia University dataset, the Indian Pines dataset, and the EO-1 dataset, indicate that SLRCNN outperforms existing state-of-the-art approaches at 4x, 5x, and 6x resolutions in both qualitative and quantitative evaluation results. Specifically, the peak signal-to-noise ratio (PSNR) of SLRCNN is improved by more than 0.9 dB, 0.9 dB, and 0.2 dB while the spectral angle mapper (SAM) is decreased by more than 0.1, 0.2, and 0.2 in degree compared to other state-of-the-art methods across three datasets, respectively, which underscores the effectiveness of SLRCNN in leveraging both spatial detail reconstruction and spectral preservation.

中文翻译：

---

SLRCNN：使用 CNN 降噪器对稀疏和低秩进行积分，以实现高光谱和多光谱图像融合


高光谱影像 （HSI） 和多光谱影像 （MSI） 的融合是生成具有增强空间分辨率的 HSI 的常用方案。目前的方法往往无法充分利用观测到的HSI和MSI中存在的有效光谱和空间先验来进一步提高聚变性能。为了解决这一限制，本文提出了一种新的HSI-MSI融合方法，该方法将稀疏和低秩与CNN降噪器（SLRCNN）集成在一起，同时考虑频谱字典优化。首先，从 HSI 派生出初始化的频谱字典。接下来，通过同时结合稀疏先验、局部低秩先验和插入图像先验来建立空间系数优化模型，其中施加 l1 范数来促进稀疏先验，并在 MSI 上进行超像素分割策略以施加局部低秩先验，同时插入训练有素的 CNN 降噪器来强制执行图像先验。然后，构建光谱字典优化模型，对初始光谱字典进行细化，捕获更详细的光谱特征，进一步改进融合结果。最后，优化过程包括应用分裂增广拉格朗日收缩法和乘子的交替方向法。模拟和真实数据集（即 Pavia University 数据集、Indian Pines 数据集和 EO-1 数据集）的实验结果表明，SLRCNN 在定性和定量评估结果中均优于 4 倍、5 倍和 6 倍分辨率的现有最先进方法。具体来说，SLRCNN 的峰值信噪比 （PSNR） 提高了 0.9 dB 、 0.9 dB 和 0 以上。2 dB，而与三个数据集中的其他最先进方法相比，频谱角度映射器 （SAM） 的度数分别降低了 0.1、0.2 和 0.2 度以上，这强调了 SLRCNN 在利用空间细节重建和频谱保留方面的有效性。