# Generating Synthetic Satellite Imagery With Deep-Learning Text-to-Image Models -- Technical Challenges and Implications for Monitoring and Verification

arXiv: https://arxiv.org/abs/2404.07754 · HTML: https://mlsanity.com/paper/2404.07754/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2024.

## Built on by (most cited first, 2 of 2)

- [Generating Synthetic Satellite Imagery for Rare Objects: An Empirical Comparison of Models and Metrics](https://mlsanity.com/paper/2409.01138/) (2024)
- [Using Game Engines and Machine Learning to Create Synthetic Satellite Imagery for a Tabletop Verification Exercise](https://mlsanity.com/paper/2404.11461/) (2024)

## Abstract (arXiv)

Novel deep-learning (DL) architectures have reached a level where they can generate digital media, including photorealistic images, that are difficult to distinguish from real data. These technologies have already been used to generate training data for Machine Learning (ML) models, and large text-to-image models like DALL-E 2, Imagen, and Stable Diffusion are achieving remarkable results in realistic high-resolution image generation. Given these developments, issues of data authentication in monitoring and verification deserve a careful and systematic analysis: How realistic are synthetic images? How easily can they be generated? How useful are they for ML researchers, and what is their potential for Open Science? In this work, we use novel DL models to explore how synthetic satellite images can be created using conditioning mechanisms. We investigate the challenges of synthetic satellite image generation and evaluate the results based on authenticity and state-of-the-art metrics. Furthermore, we investigate how synthetic data can alleviate the lack of data in the context of ML methods for remote-sensing. Finally we discuss implications of synthetic satellite imagery in the context of monitoring and verification.