Citation: Wang, F.; Zhou, G.; Hu, H.; Wang, Y.; Fu, B.; Li, S.; Xie, J. Reconstruction of LoD-2 Building Models Guided by Façade Structures from Oblique Photogrammetric Point Cloud. Remote Sens. 2023, 15, 400. https://doi.org/10.3390/rs15020400 Academic Editors: Sisi Zlatanova, Takis Mathiopoulos, Jiju Poovvancheri, Zhengxin Zhang and Dong Chen Received: 15 December 2022 Revised: 5 January 2023 Accepted: 6 January 2023 Published: 9 January 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). remote sensing Article Reconstruction of LoD-2 Building Models Guided by Façade Structures from Oblique Photogrammetric Point Cloud Feng Wang 1,2 , Guoqing Zhou 1,2, * , Han Hu 3 , Yuefeng Wang 1,2 , Bolin Fu 2 , Shiming Li 4 and Jiali Xie 2 1 Guangxi Key Laboratory of Spatial Information and Geomatics, Guilin University of Technology, Guilin 541004, China 2 College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, China 3 Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 611756, China 4 Faculty of Surveying and Geo-Informatics, North China University of Water Resources and Electric Power, Zhengzhou 450045, China * Correspondence: gzhou@glut.edu.cn; Tel.: +86-0773-5896097 Abstract: Due to the façade visibility, intuitive expression, and multi-view redundancy, oblique photogrammetry can provide optional data for large-scale urban LoD-2 reconstruction. However, the inherent noise in oblique photogrammetric point cloud resulting from the image-dense matching limits further model reconstruction applications. Thus, this paper proposes a novel method for the efficient reconstruction of LoD-2 building models guided by façade structures from an oblique photogrammetric point cloud. First, a building planar layout is constructed combined with footprint data and the vertical planes of the building based on spatial consistency constraints. The cells in the planar layout represent roof structures with a distinct altitude difference. Then, we introduce regularity constraints and a binary integer programming model to abstract the façade with the best- fitting monotonic regularized profiles. Combined with the planar layout and regularized profiles, a 2D building topology is constructed. Finally, the vertices of building roof facets can be derived from the 2D building topology, thus generating a LoD-2 building model. Experimental results using real datasets indicate that the proposed method can generate reliable reconstruction results compared with two state-of-the-art methods. Keywords: 3D reconstruction; LoD-2 model; photogrammetric point cloud; building façade 1. Introduction According to the OGC (the Open Geospatial Consortium) standard CityGML (City Geography Markup Language) [1], 3D models of buildings can be divided into multiple levels of details (LoDs), with different geometric and semantic information for varying levels of application [2]. The LoD-2 models, which distinguish between the roof and façade of buildings, form the skeleton structure of a smart city and are most widely used in urban construction and management [3]. With the rapid development of aerial vehicles and sensors, point clouds have become the primary data for three-dimensional (3D) urban reconstruction [4–6] while enabling automated 3D urban reconstruction. Light detection and ranging (LiDAR) [7,8], as an important means of 3D point cloud data acquisition, can directly obtain the position of the target, obviating the complex procedure of solving the image correspondence. Airborne laser scanning (ALS) point clouds have been widely used for 3D building reconstruction in urban areas [9] because of their short acquisition period and high accuracy. However, building façades are often missing from ALS data, especially for tall buildings [10]. In contrast, the popular oblique photogrammetry system usually carries multiple sensors with different perspectives on the airborne oblique system to collect images simultaneously [11]. Due to oblique images’ perception for complex scenes in a wide range with high accuracy, the dense matching point clouds [12] can represent Remote Sens. 2023, 15, 400. https://doi.org/10.3390/rs15020400 https://www.mdpi.com/journal/remotesensing