Abstract: Aiming at the problem that the effect of remote sensing image super-resolution reconstruction is fuzzy and the detail texture is lost in the reconstruction process, a remote sensing image super-resolution network model pDDPMSR suitable for multi-scale tasks is proposed. Firstly, an efficient pixel shift convolution module SCAM is constructed by combining shift convolution and serial multi-attention mechanism to expand the receptive field to enhance the extraction of local features, so as to improve the image clarity. At the same time, multi-attention is used to focus on the high-frequency information of the image in the channel and spatial dimensions to enhance the expression of contour detail information. Secondly, in order to prevent the loss of detailed texture, CA-ASPP is designed to fuse coordinate attention and multi-scale atrous convolutional pyramid network, so as to capture context information at different scales. Finally, the denoising diffusion probabilistic model (DDPM) is introduced to generate the high-resolution image. The layer skip sampling is used to accelerate the reasoning speed of DDPM. A nonlinear noise scheduling scheme is designed to solve the problem of excessive noise at the end of DDPM adding noise. Experimental results on the public dataset RSSCN7 show that the reconstruction effect of pDDPMSR is more significant than the comparison algorithms in peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), and the method of layer skip sampling accelerates the inference process of diffusion model by 10 times.

Key words: remote sensing image, super-resolution reconstruction, diffusion model, attention mechanism, multi-scale atrous convolution

摘要： 针对遥感图像超分辨率重建效果模糊、重建过程中细节纹理丢失的问题，提出一种适用于多尺度任务的遥感图像超分辨率网络模型pDDPMSR（denoising diffusion probabilistic model of super-resolution）。通过组合移位卷积和串联多注意力机制构建高效像素移位卷积模块SCAM（shifted convolution attention module），扩大感受野以增强对局部特征的提取能力，从而提高图像清晰度，同时使用多注意力在通道和空间维度关注图像高频信息，以增强轮廓细节信息的表达。为了防止细节纹理丢失，设计了融合坐标注意力与多尺度空洞卷积金字塔网络结构CA-ASPP（coordinate attention and atrous spatial pyramid pooling），以便捕获不同尺度的上下文信息。引入去噪扩散概率模型（denoising diffusion probabilistic model，DDPM）生成高分辨率图像，采用跳层采样加快DDPM图像推理速度。设计非线性噪声调度方案解决DDPM加噪结束时噪声过大的问题。在公开数据集RSSCN7上的实验结果表明，pDDPMSR在峰值信噪比（peak signal-to-noise ratio，PSNR）和结构相似度（structural similarity，SSIM）上较对比算法重建效果更加显著，并且跳层采样方法使扩散模型推理过程加快10倍。

关键词: 遥感图像, 超分辨率重建, 扩散模型, 注意力机制, 多尺度空洞卷积