Urban Scene Diffusion through Semantic Occupancy Map

arXiv:2403.11697v1 Announce Type: new
Abstract: Generating unbounded 3D scenes is crucial for large-scale scene understanding and simulation. Urban scenes, unlike natural landscapes, consist of various complex man-made objects and structures such as roads, traffic signs, vehicles, and buildings. To create a realistic and detailed urban scene, it is crucial to accurately represent the geometry and semantics of the underlying objects, going beyond their visual appearance. In this work, we propose UrbanDiffusion, a 3D diffusion model that is conditioned on a …

3d scenes abstract arxiv buildings cs.cv diffusion map natural objects roads scale semantic simulation through traffic type understanding urban vehicles