GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis

Srikumar Sastry, Subash Khanal, Aayush Dhakal, Nathan Jacobs
4/9/2024
cs.CV

Official code: mvrl/GeoSynth (117 stars, Apache-2.0, last commit 2024-11-29). 1 more implementation below.

Abstract

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 checkpoints are available at https://github.com/mvrl/GeoSynth.

View on arXivView PDF

Code Implementations(2)

mvrl/GeoSynthOfficial100%
Apache-2.0

A PyTorch implementation of "GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis"

11716Shell, PythonMar 15, 20241 years agoApache-2.0
diffusion-modelssatellite-imagery
KrishO9/GeoSynthforLISS4Community68%
Apache-2.0

A PyTorch implementation of "GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis"

00Shell, PythonMay 12, 20251 years agoApache-2.0

Similar Papers

TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive

84% match1 repo12026

GeoDiT: Point-Conditioned Diffusion Transformer for Satellite Image Synthesis

80% match2026

DiffusionSat: A Generative Foundation Model for Satellite Imagery

80% match1 repo2362023

RSDiff: Remote Sensing Image Generation from Text Using Diffusion Model

80% match2023

Style Alignment based Dynamic Observation Method for UAV-View Geo-localization

80% match2024

ABot-Earth 0.5: Generative 3D Earth Model

79% match2026

Cite this paper

@article{sastry2024geosynth,
  title  = {GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis},
  author = {Srikumar Sastry and Subash Khanal and Aayush Dhakal and Nathan Jacobs},
  year   = {2024},
  eprint = {2404.06637},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.06637v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.06637.svg)](https://codeofpaper.com/paper/2404.06637)

Discussion