GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis

We present GeoSynth, a model for synthesizing satellite images with global style and image-driven layout control. The global style control is via textual prompts or geographic location. These enable the specification of scene semantics or regional appearance respectively, and can be used together. W...

Full description

Saved in:
Bibliographic Details
Main Authors: Sastry, Srikumar, Khanal, Subash, Dhakal, Aayush, Jacobs, Nathan
Format: Conference Proceeding
Language:English
Subjects:
Computational modeling
Control Net
Diffusion Models
Layout
Process control
Satellite image generation
Satellite images
Semantics
Text to image
Urban planning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present GeoSynth, a model for synthesizing satellite images with global style and image-driven layout control. The global style control is via textual prompts or geographic location. These enable the specification of scene semantics or regional appearance respectively, and can be used together. We train our model on a large dataset of paired satellite imagery, with automatically generated captions, and OpenStreetMap data. We evaluate various combinations of control inputs, including different types of layout controls. Results demonstrate that our model can generate diverse, high-quality images and exhibits excellent zero-shot generalization. The code and model check-points are available at https://github.com/mvrl/GeoSynth.
ISSN:2160-7516
DOI:10.1109/CVPRW63382.2024.00051