Remote sensing image super-resolution (SR) aims to boost the image resolution while recovering rich high-frequency details. Currently, most of the SR methods are based on an assumption that the degradation kernel is a specific downsampler. However, the degradation kernel is unknown and sophisticated for real remote sensing scenes, leading to a severe performance drop. To alleviate this problem, we propose a multilayer degradation representation-guided blind SR method for remote sensing images, which mainly consists of three key steps. First, an unsupervised representation learning is exploited to learn the degradation representation from low-resolution images. Then, a degradation-guided deep residual module is designed to model high-order features across different scales from the original images. Finally, a multilayer degradation-aware feature fusion mechanism is proposed to restore the finer details. Experiments on synthetic and real datasets demonstrate that the proposed method can achieve promising performance with respect to other state-of-the-art SR approaches.

中文翻译：

---

遥感图像的多层退化表示引导的盲超分辨率

遥感图像超分辨率（SR）旨在提高图像分辨率，同时恢复丰富的高频细节。目前，大多数 SR 方法都基于退化内核是特定下采样器的假设。然而，对于真实的遥感场景，退化内核是未知且复杂的，导致性能严重下降。为了缓解这个问题，我们提出了一种多层退化表示引导的遥感图像盲SR方法，该方法主要包括三个关键步骤。首先，利用无监督表示学习从低分辨率图像中学习退化表示。然后，设计了一个退化引导的深度残差模块来对原始图像中不同尺度的高阶特征进行建模。最后，提出了一种多层退化感知特征融合机制来恢复更精细的细节。在合成数据集和真实数据集上的实验表明，所提出的方法相对于其他最先进的 SR 方法可以实现有希望的性能。