Xiao Luyang, Liao Xiangyu, Ren Chao
College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China.
Sensors (Basel). 2024 Aug 6;24(16):5098. doi: 10.3390/s24165098.
In this paper, we propose a Local Global Union Network (LGUN), which effectively combines the strengths of Transformers and Convolutional Networks to develop a lightweight and high-performance network suitable for Single Image Super-Resolution (SISR). Specifically, we make use of the advantages of Transformers to provide input-adaptation weighting and global context interaction. We also make use of the advantages of Convolutional Networks to include spatial inductive biases and local connectivity. In the shallow layer, the local spatial information is encoded by Multi-order Local Hierarchical Attention (MLHA). In the deeper layer, we utilize Dynamic Global Sparse Attention (DGSA), which is based on the Multi-stage Token Selection (MTS) strategy to model global context dependencies. Moreover, we also conduct extensive experiments on both natural and satellite datasets, acquired through optical and satellite sensors, respectively, demonstrating that LGUN outperforms existing methods.
在本文中，我们提出了一种局部全局联合网络（LGUN），它有效地结合了Transformer和卷积网络的优势，以开发一种适用于单图像超分辨率（SISR）的轻量级高性能网络。具体而言，我们利用Transformer的优势来提供输入自适应加权和全局上下文交互。我们还利用卷积网络的优势来纳入空间归纳偏差和局部连接性。在浅层，局部空间信息由多阶局部层次注意力（MLHA）进行编码。在深层，我们利用基于多阶段令牌选择（MTS）策略的动态全局稀疏注意力（DGSA）来建模全局上下文依赖性。此外，我们还分别在通过光学传感器和卫星传感器获取的自然数据集和卫星数据集上进行了广泛的实验，证明LGUN优于现有方法。
