Research on Building Holes Repair and Modeling Based on Point Clouds from Oblique Photography Reconstruction

In the context of promoting digital city infrastructure, achieving precise three dimension (3D) modeling of buildings has become increasingly vital. Oblique photogrammetry serves as a primary method for large-scale urban modeling. However, due to limitations in the capture angles and photo quality, the model generated by oblique photogrammetry often has some holes in the side of the building and the ground. To resolve this problem, this study introduces a method for building holes repair and modeling, utilizing point clouds generated from oblique photography reconstruction. The method integrates architectural knowledge and symmetry principles to devise a comprehensive scheme for repairing building surface point clouds. Based on this, the Poisson surface reconstruction algorithm are employed to reconstruct the building model, aiming to enhance both its accuracy and practicality.