MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912326575194112 |
|---|---|
| author | Borne--Pons, Paul Czerkawski, Mikolaj Martin, Rosalie Rouffet, Romain |
| author_facet | Borne--Pons, Paul Czerkawski, Mikolaj Martin, Rosalie Rouffet, Romain |
| contents | Terrain modeling has traditionally relied on procedural techniques, which often require extensive domain expertise and handcrafted rules. In this paper, we present MESA - a novel data-centric alternative by training a diffusion model on global remote sensing data. This approach leverages large-scale geospatial information to generate high-quality terrain samples from text descriptions, showcasing a flexible and scalable solution for terrain generation. The model's capabilities are demonstrated through extensive experiments, highlighting its ability to generate realistic and diverse terrain landscapes. The dataset produced to support this work, the Major TOM Core-DEM extension dataset, is released openly as a comprehensive resource for global terrain data. The results suggest that data-driven models, trained on remote sensing data, can provide a powerful tool for realistic terrain modeling and generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07210 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data Borne--Pons, Paul Czerkawski, Mikolaj Martin, Rosalie Rouffet, Romain Graphics Computer Vision and Pattern Recognition Machine Learning Terrain modeling has traditionally relied on procedural techniques, which often require extensive domain expertise and handcrafted rules. In this paper, we present MESA - a novel data-centric alternative by training a diffusion model on global remote sensing data. This approach leverages large-scale geospatial information to generate high-quality terrain samples from text descriptions, showcasing a flexible and scalable solution for terrain generation. The model's capabilities are demonstrated through extensive experiments, highlighting its ability to generate realistic and diverse terrain landscapes. The dataset produced to support this work, the Major TOM Core-DEM extension dataset, is released openly as a comprehensive resource for global terrain data. The results suggest that data-driven models, trained on remote sensing data, can provide a powerful tool for realistic terrain modeling and generation. |
| title | MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data |
| topic | Graphics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2504.07210 |