Conventional deep learning-based methods for single remote sensing image super-resolution (SRSISR) have made remarkable progress. However, the super-resolution (SR) outputs of these methods are yet to become sufficiently satisfactory in visual quality. Recent diffusion model-based generative deep learning models are capable to enhance the visual quality of output images, but this capability is limited due to their sampling efficiency. In this article, we propose FastDiffSR, an SRSISR method based on a conditional diffusion model. Specifically, we devise a novel sampling strategy to reduce the number of sampling steps required by the diffusion model while ensuring the sampling quality. Meanwhile, the residual image is adopted to reduce computational costs, demonstrating that integrating channel attention and spatial attention begets a further improvement in the visual quality of output images. Compared to the state-of-the-art (SOTA) convolutional neural network (CNN)-based, GAN-based, and Transformer-based SR methods, our FastDiffSR improves the learned perceptual image patch similarity (LPIPS) by 0.1–0.2 and achieves better visual results in some real-world scenes. Compared with existing diffusion-based SR methods, our FastDiffSR achieves significant improvements in pixel-level evaluation metric peak signal-noise ratio (PSNR) while having smaller model parameters and obtaining better SR results on Vaihingen data with faster inference time by 2.8–28 times, showing excellent generalization ability and time efficiency. Our code will be open source at https://github.com/Meng-333/FastDiffSR .

中文翻译：

---

遥感图像超分辨率快速采样条件扩散模型


传统的基于深度学习的单幅遥感图像超分辨率（SRSISR）方法已经取得了显着的进展。然而，这些方法的超分辨率（SR）输出在视觉质量方面还不够令人满意。最近基于扩散模型的生成深度学习模型能够增强输出图像的视觉质量，但由于采样效率的原因，这种能力受到限制。在本文中，我们提出了FastDiffSR，一种基于条件扩散模型的SRSISR方法。具体来说，我们设计了一种新颖的采样策略，以减少扩散模型所需的采样步骤数，同时保证采样质量。同时，采用残差图像来降低计算成本，表明通道注意力和空间注意力的结合可以进一步提高输出图像的视觉质量。与最先进的 (SOTA) 基于卷积神经网络 (CNN)、基于 GAN 和基于 Transformer 的 SR 方法相比，我们的 FastDiffSR 将学习感知图像块相似度 (LPIPS) 提高了 0.1–0.2在一些现实场景中取得更好的视觉效果。与现有的基于扩散的 SR 方法相比，我们的 FastDiffSR 在像素级评估指标峰值信噪比 (PSNR) 方面取得了显着改进，同时具有更小的模型参数，并在 Vaihingen 数据上获得了更好的 SR 结果，推理时间加快了 2.8-28 倍，表现出出色的泛化能力和时间效率。我们的代码将在 https://github.com/Meng-333/FastDiffSR 开源。