# Generating Synthetic Satellite Imagery for Rare Objects: An Empirical Comparison of Models and Metrics

arXiv: https://arxiv.org/abs/2409.01138 · HTML: https://mlsanity.com/paper/2409.01138/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 56 references that are in the map.
- First posted on arXiv 2 Sep 2024.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers](https://mlsanity.com/paper/2204.14217/) (2022)
- [A Note on the Inception Score](https://mlsanity.com/paper/1801.01973/) (2018)
- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry](https://mlsanity.com/paper/2307.12868/) (2023)
- [Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains](https://mlsanity.com/paper/2210.04133/) (2022)
- [HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models](https://mlsanity.com/paper/1904.01121/) (2019)
- [RarePlanes: Synthetic Data Takes Flight](https://mlsanity.com/paper/2006.02963/) (2020)
- [Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks](https://mlsanity.com/paper/2208.04441/) (2022)
- [Artificial Intelligence for Social Good: A Survey](https://mlsanity.com/paper/2001.01818/) (2020)
- [Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies](https://mlsanity.com/paper/2012.13736/) (2020)
- [The Synthinel-1 dataset: a collection of high resolution synthetic overhead imagery for building segmentation](https://mlsanity.com/paper/2001.05130/) (2020)
- [Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis](https://mlsanity.com/paper/1910.10223/) (2019)
- [Approximating Human Judgment of Generated Image Quality](https://mlsanity.com/paper/1912.12121/) (2019)
- [Generating Synthetic Satellite Imagery With Deep-Learning Text-to-Image Models -- Technical Challenges and Implications for Monitoring and Verification](https://mlsanity.com/paper/2404.07754/) (2024)

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

- [CAFOSat: A Strongly Annotated Dataset for Infrastructure-Aware CAFO Mapping Using High-Resolution Imagery](https://mlsanity.com/paper/2606.00548/) (2026)
- [Synthetic Data Augmentation for Satellite-Based Analysis of Battle-Damaged Agricultural Fields in Ukraine](https://mlsanity.com/paper/2608.16380/) (2026)

## Abstract (arXiv)

Generative deep learning architectures can produce realistic, high-resolution fake imagery -- with potentially drastic societal implications. A key question in this context is: How easy is it to generate realistic imagery, in particular for niche domains. The iterative process required to achieve specific image content is difficult to automate and control. Especially for rare classes, it remains difficult to assess fidelity, meaning whether generative approaches produce realistic imagery and alignment, meaning how (well) the generation can be guided by human input. In this work, we present a large-scale empirical evaluation of generative architectures which we fine-tuned to generate synthetic satellite imagery. We focus on nuclear power plants as an example of a rare object category - as there are only around 400 facilities worldwide, this restriction is exemplary for many other scenarios in which training and test data is limited by the restricted number of occurrences of real-world examples. We generate synthetic imagery by conditioning on two kinds of modalities, textual input and image input obtained from a game engine that allows for detailed specification of the building layout. The generated images are assessed by commonly used metrics for automatic evaluation and then compared with human judgement from our conducted user studies to assess their trustworthiness. Our results demonstrate that even for rare objects, generation of authentic synthetic satellite imagery with textual or detailed building layouts is feasible. In line with previous work, we find that automated metrics are often not aligned with human perception -- in fact, we find strong negative correlations between commonly used image quality metrics and human ratings.