Remote Sensing Image Super-Resolution via Residual Aggregation and Split Attentional Fusion Network

Abstract

Remote sensing images contain various land surface scenes and different scales of ground objects, which greatly increases the difficulty of super-resolution tasks. The existing deep learning-based methods cannot solve this problem well. To achieve high-quality super-resolution of remote sensing images, a residual aggregation and split attentional fusion network (RASAF) is proposed in this article. It is mainly divided into the following three parts. First, a split attentional fusion block is proposed. It uses a basic split-fusion mechanism to achieve cross-channel feature group interaction, allowing the method to adapt to various land surface scene reconstructions. Second, to fully exploit multi-scale image information, a hierarchical loss function is used. Third, residual learning is used to reduce the difficulty of training in super-resolution tasks. However, the respective residual branch features are used quite locally and fail to represent the real value. A residual aggregation mechanism is used to aggregate the local residual branch features to generate higher quality local residual branch features. The comparison of RASAF with some classical super-resolution methods using two widely used remote sensing datasets showed that the RASAF achieved better performance. And it achieves a good balance between performance and model parameter number. Meanwhile, the RASAF's ability to support multi-label remote sensing image classification tasks demonstrates its usefulness.

Resolution-Agnostic Remote Sensing Scene Classification With Implicit Neural Representations

“…Wang et al [43] construct a lightweight feature enhancement network to achieve a good trade-off between model complexity and performance for remote sensing images. Chen et al [15] propose a U-Net like network combined with a split attentional fusion model to obtain HR remote sensing images. Moreover, GAN is also introduced to improve the visual super-resolved results for remote sensing LR images.…”

“…I MAGE super-resolution (SR), as a vital technique for elevating image and video spatial resolution, has found vast applications in medical imaging [1,2], surveillance and security [3,4], and remote sensing image analysis [5][6][7], etc. Particularly, remote sensing applications including object detection and recognition [8][9][10][11], semantic segmentation [12][13][14], and change detection [15] require high-resolution (HR) images with rich high-frequency details and texture information to perform effective image discrimination, analysis, interpretation, and perception. In face of the forbidden cost in image acquisition, SR becomes indispensable for remote sensing image applications.…”

Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution

“…Thus, attention mechanism was introduced to the field of remote sensing image SR. HSENet [28] exploits the single-scale and cross-scale self-similarity information using multi-scale Non-Local attention. A split attention fusion block was established by Chen et al [2] allowing the method to adapt to varied multi-scale land surface reconstructions. Rather of exploring first-order attention (channel or spatial statistics), Zhang et al [29] advocated a high-order attention block to restore the missing details.…”

“…Some recent work has initiated efforts in this direction. Residual aggregation and split attention fusion network [2] uses a UNet-based encoder and decoder structure to extract both shallow semantic information and high-level features. Although this approach is capable of extracting multi-scale features, it leads to irreversible information loss through frequent up and down sampling, which will eventually affect the reconstruction results.…”

MSLAENet: Multiscale Learning and Attention Enhancement Network for Fusion Classification of Hyperspectral and LiDAR Data

“…Many studies have shown that deep learning has achieved remarkable results in the fields of single-source remote sensing image (e.g., HSI, MSI, LiDAR, etc.) classification [18][19][20], semantic segmentation [21][22], and super-resolution [23]. In order to fully utilize the complementary information of multimodal remote sensing images, many excellent deep learning methods have been proposed, and typical models include convolutional neural networks (CNN), recurrent neural networks, and autoencoder networks.…”