GS2Poly: Textured Polygonal Building Reconstruction Guided by Gaussian Opacity Fields

Compact low-poly building models with concise structures and texture fidelity are essential infrastructure for digital twin cities. Traditional point cloud-based reconstruction methods often rely on surface normals, and the presence of missing data and noise poses significant challenges for accurate reconstruction. In this article, we propose GS2Poly, a textured polygonal mesh reconstruction method for buildings based on the 3-D Gaussian splatting (3DGS) framework. First, 3DGS of the building scene is reconstructed under planar structure constraints. A density-weighted Gaussian sampling method is utilized to sample high-quality surface point clouds and extract planar primitives from 3DGS reconstruction results. Next, GS2Poly applies an adaptive spatial partitioning strategy to generate a set of candidate convex polyhedra. Finally, guided by the Gaussian opacity field (GOF), a Markov random field (MRF) is constructed to extract the polygonal mesh surface, followed by high-fidelity texture mapping using an optimal rendering strategy. Experimental results across diverse building scenarios demonstrate that GS2Poly exhibits higher geometric fidelity than spatial partitioning-based or 3DGS-based mesh simplification methods. In addition, the proposed texture mapping strategy effectively avoids typical texture artifacts such as occlusion, seams, and distortions.