# MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data

arXiv: https://arxiv.org/abs/2504.07210 · HTML: https://mlsanity.com/paper/2504.07210/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation](https://mlsanity.com/paper/2303.00848/) (2023)
- [RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion models](https://mlsanity.com/paper/2405.00666/) (2024)
- [DiffusionSat: A Generative Foundation Model for Satellite Imagery](https://mlsanity.com/paper/2312.03606/) (2023)
- [HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion](https://mlsanity.com/paper/2310.08579/) (2023)
- [GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis](https://mlsanity.com/paper/2404.06637/) (2024)
- [Generate Your Own Scotland: Satellite Image Generation Conditioned on Maps](https://mlsanity.com/paper/2308.16648/) (2023)
- [From LAION-5B to LAION-EO: Filtering Billions of Images Using Anchor Datasets for Satellite Image Extraction](https://mlsanity.com/paper/2309.15535/) (2023)
- [SEnSeI: A Deep Learning Module for Creating Sensor Independent Cloud Masks](https://mlsanity.com/paper/2111.08349/) (2021)

## Built on by (most cited first, 7 of 7)

- [COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails](https://mlsanity.com/paper/2504.08548/) (2025)
- [TerraFusion: Joint Generation of Terrain Geometry and Texture Using Latent Diffusion Models](https://mlsanity.com/paper/2505.04050/) (2025)
- [InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation](https://mlsanity.com/paper/2512.08309/) (2025)
- [COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data](https://mlsanity.com/paper/2603.03239/) (2026)
- [Geodiffussr: Generative Terrain Texturing with Elevation Fidelity](https://mlsanity.com/paper/2511.23029/) (2025)
- [Enhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal Conditioning](https://mlsanity.com/paper/2609.31199/) (2026)
- [WorldWeave: Growing Persistent Geometric Worlds for Video Generation](https://mlsanity.com/paper/2609.34221/) (2026)

## Abstract (arXiv)

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.