SF-Recon: Simplification-Free Lightweight Building Reconstruction via 3D Gaussian Splatting

TL;DR

SF-Recon introduces a novel method for directly reconstructing lightweight building surface models from multi-view images without the need for mesh simplification, combining Gaussian Splatting and edge-guided optimization.

Contribution

The paper presents SF-Recon, a new approach that reconstructs lightweight building models directly from images using Gaussian Splatting and structural optimization, eliminating post-processing steps.

Findings

Reconstructs models with fewer faces and vertices.

Maintains structural accuracy and sharpness.

Operates efficiently without external supervision.

Abstract

Lightweight building surface models are crucial for digital city, navigation, and fast geospatial analytics, yet conventional multi-view geometry pipelines remain cumbersome and quality-sensitive due to their reliance on dense reconstruction, meshing, and subsequent simplification. This work presents SF-Recon, a method that directly reconstructs lightweight building surfaces from multi-view images without post-hoc mesh simplification. We first train an initial 3D Gaussian Splatting (3DGS) field to obtain a view-consistent representation. Building structure is then distilled by a normal-gradient-guided Gaussian optimization that selects primitives aligned with roof and wall boundaries, followed by multi-view edge-consistency pruning to enhance structural sharpness and suppress non-structural artifacts without external supervision. Finally, a multi-view depth-constrained Delaunay triangulation converts the structured Gaussian field into a lightweight, structurally faithful building mesh. Based on a proposed SF dataset, the experimental results demonstrate that our SF-Recon can directly reconstruct lightweight building models from multi-view imagery, achieving substantially fewer faces and vertices while maintaining computational efficiency. Website:https://lzh282140127-cell.github.io/SF-Recon-project/