Short
CityDreamer, a generative AI model, creates unbounded 3D cities by separating the generation of building instances from other background objects. This model allows for better handling of the diverse appearance of buildings in urban environments - one of the main challenges compared to generating natural environments, as methods such as GANCraft do.
To enhance the realism of the generated 3D cities, the authors constructed two datasets, OSM and GoogleEarth, which provide more realistic city layouts and appearances, easily scalable to other cities worldwide.
