Optimal Model Fitting for Building Reconstruction From Point Clouds

Abstract

Geometric-semantic coherent building models are demanding in many geoscience applications. Conventional building modeling methods often rely on successive roof plane segmentation and fitting. The subsequent reconstruction procedure is difficult to assure topologic consistency and geometric accuracy. This paper starts with a library of predefined building models or primitives, including pyramid, gable, hip, etc. We propose an optimal model fitting approach that holistically determines all of its parameters from segmented point cloud data. The approach is formulated as an optimization problem that minimizes the point-to-mesh distance between the point cloud and the meshed primitive model. Necessary constraints in the form of inequality equations are introduced to assure correct and reliable solution. For complex roofs consisting of several predefined primitive models, a hierarchical procedure is presented to reconstruct the major roof model and its superstructures sequentially. The CityGML LoD2 model is created from the parameterized primitives. The quality and performance of this approach are evaluated with airborne lidar and photogrammetric point clouds. Based on the experiments with 910 buildings, the primitive fitting accuracy is 7.8cm and the corner uncertainty is 0.36m or 0.78 times the ground point spacing; the building boundary consistency is 89.6%. The study demonstrates a piecewise continuous polyhedral building model can be determined through a holistic parameter optimization process. The resultant building models intrinsically best fit to the input point cloud with topologic integrity. The approach not only qualitatively generates semantic building models, but also exhibits the potential for building reconstruction over large areas.

Deep Learning for 3d Building Reconstruction: A Review

“…Their approach consists of three parts: Scale-ONet for model reconstruction, Optim-Net for model scale optimization, and Model-Image match for restoring reconstructed scenes. The holistic primitive fitting method (Zhang et al, 2021) was also used along with PointNet++ (Qi et al, 2017) for 3D building reconstruction from point clouds. Another three-step 3D building reconstruction approach using deep implicit fields and point clouds was proposed by Chen et al (2021).…”

Iterative Low-Poly Building Model Reconstruction from Mesh Soups Based on Contour

“…Model-based methods produce stable results on complex or broken structures by predefining templates with prior knowledge. These templates usually take into account the roof shapes and substructures such as windows and chimneys [18]. The predefined templates are recognized from the input data, and then, suitable parameters are determined by solving an optimization problem [18][19][20].…”

“…These templates usually take into account the roof shapes and substructures such as windows and chimneys [18]. The predefined templates are recognized from the input data, and then, suitable parameters are determined by solving an optimization problem [18][19][20]. Deep learning is also utilized in recent studies.…”

Deep Learning for Semantic 3d City Model Extension: Modeling Roof Superstructures Using Aerial Images for Solar Potential Analysis

“…Conventional building reconstruction methods can be classified into data-driven and model-driven approaches. Data driven methods rely on the fitting of individuals planes to reconstruct buildings, while modeldriven approaches operate by estimating the parameters of predefined primitives Zhang et al (2021). Due to rapid developments in airborne laser scanning and stereo photogrammetry, a variety of algorithms have been proposed to generate 3D building models up to LoD2 from point clouds.…”

“…The authors are able to detect flat superstructures (skylights) using a template matching approach. Zhang et al (2021) introduced a reconstruction procedure to derive a CityGML LoD2 model with superstructures modeled as building installation objects from point clouds. For the reconstruction of complex roofs a hierarchical procedure is presented to reconstruct the major roof model and its superstructures sequentially based on primitive parameterization and recognition.…”