CityDreamer: Compositional Generative Model of Unbounded 3D Cities

arXiv:2309.00610v2 Announce Type: replace
Abstract: 3D city generation is a desirable yet challenging task, since humans are more sensitive to structural distortions in urban environments. Additionally, generating 3D cities is more complex than 3D natural scenes since buildings, as objects of the same class, exhibit a wider range of appearances compared to the relatively consistent appearance of objects like trees in natural scenes. To address these challenges, we propose \textbf{CityDreamer}, a compositional generative model designed specifically for unbounded 3D cities. …

abstract arxiv buildings cities city class cs.cv environments generative humans natural objects type urban