---
license: other
license_name: adobe-license
license_link: LICENSE
datasets:
- Major-TOM/Core-S2L2A
- Major-TOM/Core-DEM
---
MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data
Paul Borne--Pons, Mikolaj Czerkawski,Rosalie Martin,
Romain Rouffet
CVPR 2025 Workshop MORSE
MESA is a novel generative model based on latent denoising diffusion capable of generating 2.5D representations of terrain based on the text prompt conditioning supplied via natural language. The model produces two co-registered modalities of optical and depth maps.
## Model Description
- **Paper:** [MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data](https://arxiv.org/abs/2504.07210)
- **Github:**
- **Project page:**
- **License:** [Adobe License](https://huggingface.co/NewtNewt)
## Installation
```sh
# Clone the repository
git clone https://github.com/PaulBorneP/MESA.git
cd MESA
```
## Model Download
```sh
huggingface-cli download NewtNewt/MESA --local-dir ./weights
```
```latex
@inproceedings{mesa2025,
title={MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data},
author={Paul Borne--Pons and Mikolaj Czerkawski and Rosalie Martin and Romain Rouffet},
year={2025},
booktitle={MORSE Workshop at CVPR 2025},
eprint={2504.07210},
url={https://arxiv.org/abs/2504.07210},}
```
## Acknowledgements
This implementation builds upon Hugging Face’s [Diffusers](https://github.com/huggingface/diffusers) library. We also acknowledge [Gradio](https://www.gradio.app/) for providing an easy-to-use interface that allowed us to create the inference demos for our models.
This model is the product of a collaboration between [Φ-lab, European Space Agency (ESA)](https://philab.esa.int/) and the [Adobe Research (Paris, France)](https://research.adobe.com/careers/paris/).