EarthGen: Generating the World from Top-Down Views
This enables scalable creation of realistic Earth surfaces for applications like interactive maps and 3D scene generation, though it builds incrementally on existing diffusion and tiling techniques.
The paper tackles the problem of generating extensive, high-resolution terrain models by developing a cascade of superresolution diffusion models combined with tiled generation, achieving superior performance on extreme 1024x zoom super-resolution tasks compared to baselines.
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.