MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data
This provides a scalable solution for terrain generation, benefiting fields like simulation and gaming, though it is incremental as it applies existing diffusion methods to a new domain.
The paper tackles terrain modeling by training a diffusion model on global remote sensing data to generate terrain from text descriptions, resulting in realistic and diverse landscapes with the release of a new dataset.
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.