AI RESEARCH
GS4City: Hierarchical Semantic Gaussian Splatting via City-Model Priors
arXiv CS.CV
•
ArXi:2604.11401v1 Announce Type: new Recent semantic 3D Gaussian Splatting (3DGS) methods primarily rely on 2D foundation models, often yielding ambiguous boundaries and limited for structured urban semantics. While city models such as CityGML encode hierarchically organized semantics together with building geometry, these labels cannot be directly mapped to Gaussian primitives. We present GS4City, a hierarchical semantic Gaussian Splatting method that incorporates city-model priors for urban scene understanding.