An increasing number of applications require the accurate 3D layout reconstruction of indoor environments. Various devices including laser scanners and color and depth (RGB-D) cameras can be used for this purpose and provide abundant and highly precise data sources. However, due to indoor environment complexity, existing noise and occlusions caused by clutter in acquired data, current studies often require the idealization of the architecture space or add an implication hypothesis to input data as priors, which limits the use of these methods for general purposes. In this study, we propose a general 3D layout reconstruction method for indoor environments. The method combines voxel-based room segmentation and space partition to build optimum polygonal models. It releases idealization of the architectural space into a non-Manhattan world and can accommodate various types of input data sources, including both point clouds and meshes. A total of four point cloud datasets, four mesh datasets and two cross-floor datasets were used in experiments. The results exhibit more than 80% completeness and correctness as well as high accuracy.

Room segmentation is a basic task for the semantic enrichment of point clouds. Recent studies have mainly projected single-floor point clouds to binary images to realize two-dimensional room segmentation. However, these methods have difficulty solving semantic segmentation problems in complex 3D indoor environments, including cross-floor spaces and rooms inside rooms; this is the bottleneck of indoor 3D modeling for non-Manhattan worlds. To make full use of the abundant geometric and spatial structure information in 3D space, a novel 3D room segmentation method that realizes room segmentation directly in 3D space is proposed in this study. The method utilizes volumetric representation based on a VDB data structure and packs an indoor space with a set of compact spheres to form rooms as separated connected components. Experimental results on different types of indoor point cloud datasets demonstrate the efficiency of the proposed method.

Ancient Chinese architecture, with its typical symmetrical structures, curved roofs, and upturned eaves presenting a unique architectural aesthetic, is a treasure of Chinese culture. Recently, unmanned aerial vehicle oblique photogrammetry and laser scanning technology have greatly facilitated the realistic replication of ancient buildings and have become crucial data sources for the HBIM of ancient buildings. However, parameter extraction and geometric model representation are more difficult because of the curved surfaces and upturned eaves of traditional Chinese roofs. As symmetrical features are typical of ancient Chinese architecture, the parameter quantity and modelling difficulty of the model representation can be effectively reduced by recognizing the symmetrical structure of traditional Chinese roofs and using “mirror replication” to quickly generate the other half of the model. Accurate symmetry detection and highly efficient parameter extraction are crucial for the HBIM of traditional Chinese roofs. Therefore, in this study, a deep learning network, namely, TCRSym-Net, is proposed to identify the symmetry from point clouds of traditional Chinese roofs. Each roof point cloud is then relocated and reoriented to obtain longitudinal and cross sections, and parametric modelling scripts are coded in Dynamo to model traditional Chinese roofs via curve lofting and solid Boolean operations. The experimental results reveal that the symmetry detection network is effective for symmetry detection, and five different types of traditional Chinese roofs are successfully recreated, which confirms the dependability of the method.