This repository is the official implementation of GeoSynth [CVPRW, EarthVision, 2024]. GeoSynth is a suite of models for synthesizing satellite images with global style and image-driven layout control.
Models available in π€ HuggingFace diffusers:
All model ckpt
files available here - Model Zoo
- Update Gradio demo
- Release Location-Aware GeoSynth Models to π€ HuggingFace
- Release PyTorch
ckpt
files for all models - Release GeoSynth Models to π€ HuggingFace
Example inference using π€ HuggingFace pipeline:
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
import torch
from PIL import Image
img = Image.open("osm_tile_18_42048_101323.jpeg")
controlnet = ControlNetModel.from_pretrained("MVRL/GeoSynth-OSM")
pipe = StableDiffusionControlNetPipeline.from_pretrained("stabilityai/stable-diffusion-2-1-base", controlnet=controlnet)
pipe = pipe.to("cuda:0")
# generate image
generator = torch.manual_seed(10345340)
image = pipe(
"Satellite image features a city neighborhood",
generator=generator,
image=img,
).images[0]
image.save("generated_city.jpg")
Our model is able to synthesize based on high-level geography of a region:
Look at train.md for details on setting up the environment and training models on your own data.
Download GeoSynth models from the given links below:
Control | Location | Download Url |
---|---|---|
- | β | Link |
OSM | β | Link |
SAM | β | Link |
Canny | β | Link |
- | β | Link |
OSM | β | Link |
SAM | β | Link |
Canny | β | Link |
@inproceedings{sastry2024geosynth,
title={GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis},
author={Sastry, Srikumar and Khanal, Subash and Dhakal, Aayush and Jacobs, Nathan},
booktitle={IEEE/ISPRS Workshop: Large Scale Computer Vision for Remote Sensing (EARTHVISION),
year={2024}
}
Check out our lab website for other interesting works on geospatial understanding and mapping: