用全球遥感数据训练扩散模型，实现文本驱动的逼真地形生成。
MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data
- 基于全球遥感数据训练扩散模型，从文本生成地形
- 生成地形多样且逼真，支持大规模地理场景建模
- 开源核心数据集，适合地理建模与生成式AI研究者
传统地形建模依赖过程化方法，需大量领域知识和手工规则。本文提出MESA——一种以数据为中心的新方法，通过在大规模遥感数据上训练扩散模型，实现从文本描述生成高质量地形样本。该方法充分利用全球地理空间信息，展示出灵活且可扩展的地形生成能力。实验表明，模型能生成真实且多样的地形景观。为支持本工作，我们发布了开源数据集Major TOM Core-DEM extension，作为全球地形数据的综合性资源。结果表明，基于遥感数据训练的数据驱动模型，可成为真实地形建模的强大工具。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。