GS4Buildings: Prior-Guided Gaussian Splatting for 3D Building Reconstruction

TL;DR

GS4Buildings introduces a prior-guided Gaussian Splatting approach that leverages semantic 3D building models to enhance large-scale urban building reconstruction, achieving higher completeness and accuracy.

Contribution

It proposes a novel method that initializes Gaussian primitives from semantic models and incorporates prior depth and normal maps for improved urban building reconstruction.

Findings

Reconstruction completeness improved by 20.5%.

Geometric accuracy increased by 32.8%.

Reduced Gaussian primitives by 71.8% in building-focused mode.

Abstract

Recent advances in Gaussian Splatting (GS) have demonstrated its effectiveness in photo-realistic rendering and 3D reconstruction. Among these, 2D Gaussian Splatting (2DGS) is particularly suitable for surface reconstruction due to its flattened Gaussian representation and integrated normal regularization. However, its performance often degrades in large-scale and complex urban scenes with frequent occlusions, leading to incomplete building reconstructions. We propose GS4Buildings, a novel prior-guided Gaussian Splatting method leveraging the ubiquity of semantic 3D building models for robust and scalable building surface reconstruction. Instead of relying on traditional Structure-from-Motion (SfM) pipelines, GS4Buildings initializes Gaussians directly from low-level Level of Detail (LoD)2 semantic 3D building models. Moreover, we generate prior depth and normal maps from the planar building geometry and incorporate them into the optimization process, providing strong geometric guidance for surface consistency and structural accuracy. We also introduce an optional building-focused mode that limits reconstruction to building regions, achieving a 71.8% reduction in Gaussian primitives and enabling a more efficient and compact representation. Experiments on urban datasets demonstrate that GS4Buildings improves reconstruction completeness by 20.5% and geometric accuracy by 32.8%. These results highlight the potential of semantic building model integration to advance GS-based reconstruction toward real-world urban applications such as smart cities and digital twins. Our project is available: https://github.com/zqlin0521/GS4Buildings.