In recent years, the powerful nonlinear modeling capability of convolutional neural networks (CNN) has led to an increasing number of researchers focusing on deep-learning-based pansharpening methods. However, due to the diversity of remote sensing image features and the limitations of the convolution operation, the existing methods are still inadequate in restoring the spatial details of complex remote sensing scenes. Therefore, in this article, we propose a simple and effective network for pansharpening methods. Specifically, in our hierarchical feature integration architecture, a multiscale grouping dilated block is designed to adequately capture fine-grained representations of multilevel scale features. At the same time, we propose a spatially self-attention block to adaptively improve the feature extraction process by establishing associations between features. The above blocks are connected in a hierarchical design, with selective reuse of features between layers and a good ability to explore new levels of features while reusing low-level features. Our experiments with the GaoFen-2 satellite dataset, WorldView-2 satellite dataset, and WorldView-3 satellite dataset show that our proposed method is highly competitive with the existing excellent methods in both objective indicator evaluation and subjective visual evaluation.

中文翻译：

---

MHANet：具有自适应优化的多尺度分层全色锐化方法

近年来，卷积神经网络（CNN）强大的非线性建模能力导致越来越多的研究人员专注于基于深度学习的全色锐化方法。然而，由于遥感图像特征的多样性和卷积运算的局限性，现有方法在恢复复杂遥感场景的空间细节方面仍存在不足。因此，在本文中，我们提出了一种简单有效的全色锐化方法网络。具体来说，在我们的分层特征集成架构中，设计了一个多尺度分组扩张块以充分捕获多层次尺度特征的细粒度表示。同时，我们提出了一个空间自注意力块，通过建立特征之间的关联来自适应地改进特征提取过程。上述块以分层设计连接，在层之间选择性地重用特征，并且在重用低级特征的同时具有探索新级别特征的良好能力。我们在高分二号卫星数据集、WorldView-2 卫星数据集和 WorldView-3 卫星数据集上的实验表明，我们提出的方法在客观指标评估和主观视觉评估方面与现有的优秀方法具有很强的竞争力。