Generate Your Own Scotland: Satellite Image Generation Conditioned on Maps
Miguel Espinosa, Elliot J. Crowley

TL;DR
This paper demonstrates that pretrained diffusion models can generate realistic satellite images conditioned on cartographic data, using new datasets and ControlNet training, highlighting potential applications and challenges in Earth Observation.
Contribution
It introduces a method to condition diffusion models on maps for satellite image generation and provides datasets and code for further research.
Findings
High-quality satellite images conditioned on maps are achievable.
ControlNet effectively incorporates cartographic data into image generation.
The approach opens new avenues for remote sensing applications.
Abstract
Despite recent advancements in image generation, diffusion models still remain largely underexplored in Earth Observation. In this paper we show that state-of-the-art pretrained diffusion models can be conditioned on cartographic data to generate realistic satellite images. We provide two large datasets of paired OpenStreetMap images and satellite views over the region of Mainland Scotland and the Central Belt. We train a ControlNet model and qualitatively evaluate the results, demonstrating that both image quality and map fidelity are possible. Finally, we provide some insights on the opportunities and challenges of applying these models for remote sensing. Our model weights and code for creating the dataset are publicly available at https://github.com/miquel-espinosa/map-sat.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsColorectal Cancer Screening and Detection · Hydrology and Watershed Management Studies · Gut microbiota and health
MethodsDiffusion
