3D Reconstruction of UAV Building Point Clouds via Corner Detection Based on Line Symmetric Bilateral Point Distribution Features

Abstract

Reconstructing 3D building models from point clouds acquired by UAV sensors remains challenging due to irregular building geometries and sensor noise. This paper proposes an unsupervised, geometry-oriented reconstruction method based on the line-symmetric bilateral point distribution features. The method constructs baselines from farthest point pairs within local bounding spheres, then applies dual-parameter constraints (point–line distance and point statistics on both sides of a line of symmetry) combined with density peak ranking to detect building corners without training data. Evaluations show that the method reduces Cloud-to-Mesh error by 15–20% over Polyfit, DIF method, and PolyGNN, while retaining fine details in complex L-shaped and U-shaped buildings. Reconstruction quality remains stable under 0.05 m Gaussian noise. The training-free, lightweight design enables scalable, automated 3D building reconstruction for digital-twin applications.