用分层扩散模型生成千米级高分辨率地球地形，支持交互式超大图
EarthGen: Generating the World from Top-Down Views
- 分层超分扩散模型+瓦片生成，实现多尺度一致地形合成
- 1024倍超分任务下超越基线，生成千平方公里级真实地貌
- 适合地图生成、虚拟世界构建等需要海量一致场景的领域
本文提出一种全新的大规模多尺度生成式地形建模方法。核心是级联的超分辨率扩散模型，可组合生成跨多分辨率的一致图像。结合瓦片生成策略，构建了一个可扩展系统，能在高分辨率下生成数千平方公里的逼真地球表面。在从Bing Maps收集的数据集上评估表明，该方法在1024倍超分任务中优于现有超分基线。同时，通过交互式吉比特级生成地图，展示了其生成多样化且连贯场景的能力。最后，证明了系统可扩展至可控世界生成和3D场景生成等新型内容创作应用。
原文摘要 · Abstract (English)
In this work, we present a novel method for extensive multi-scale generative terrain modeling. At the core of our model is a cascade of superresolution diffusion models that can be combined to produce consistent images across multiple resolutions. Pairing this concept with a tiled generation method yields a scalable system that can generate thousands of square kilometers of realistic Earth surfaces at high resolution. We evaluate our method on a dataset collected from Bing Maps and show that it outperforms super-resolution baselines on the extreme super-resolution task of 1024x zoom. We also demonstrate its ability to create diverse and coherent scenes via an interactive gigapixel-scale generated map. Finally, we demonstrate how our system can be extended to enable novel content creation applications including controllable world generation and 3D scene 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。