The paper investigates the utility of text-to-image inpainting models for satellite image data. Two technical challenges of injecting structural guiding signals into the generative process as well as translating the inpainted RGB pixels to a wider set of MSI bands are addressed by introducing a novel inpainting framework based on StableDiffusion and ControlNet as well as a novel method for RGB-to-MSI translation. The results on a wider set of data suggest that the inpainting synthesized via StableDiffusion suffers from undesired artefacts and that a simple alternative of self-supervised internal inpainting achieves higher quality of synthesis.

翻译：本文研究了文本到图像修复模型在卫星图像数据中的实用性。针对在生成过程中注入结构引导信号以及将修复后的RGB像素转换为更广泛的多光谱（MSI）波段集这两项技术挑战，我们提出了一种基于StableDiffusion和ControlNet的新型修复框架，以及一种用于RGB到MSI转换的新方法。在更广泛数据集上的结果表明，通过StableDiffusion合成的修复结果存在不期望的伪影，而一种简单的自监督内部修复替代方案可实现更高质量的合成。