Diffusion models have achieved state-of-the-art results on many modalities including images, speech, and video. However, existing models are not tailored to support remote sensing data, which is widely used in important applications including environmental monitoring and crop-yield prediction. Satellite images are significantly different from natural images -- they can be multi-spectral, irregularly sampled across time -- and existing diffusion models trained on images from the Web do not support them. Furthermore, remote sensing data is inherently spatio-temporal, requiring conditional generation tasks not supported by traditional methods based on captions or images. In this paper, we present DiffusionSat, to date the largest generative foundation model trained on a collection of publicly available large, high-resolution remote sensing datasets. As text-based captions are sparsely available for satellite images, we incorporate the associated metadata such as geolocation as conditioning information. Our method produces realistic samples and can be used to solve multiple generative tasks including temporal generation, superresolution given multi-spectral inputs and in-painting. Our method outperforms previous state-of-the-art methods for satellite image generation and is the first large-scale $\textit{generative}$ foundation model for satellite imagery.

DiffusionSat是迄今为止最大的生成基础模型，使用公开可获得的大型高分辨率遥感数据集进行训练，实现对多个生成任务的解决，包括时间生成、多光谱输入的超分辨率和修复。同时它在卫星图像生成方面优于以前的最先进方法，也是第一个针对卫星图像的大规模生成基础模型。

DiffusionSat：卫星遥感图像的生成基础模型