Jul 2026· The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences· Vol XLIX-B2-2026, pp. 1237-1243· 0 citations· 11 references
Abstract
Abstract. This paper presents a comprehensive methodology for the automated semantic segmentation and 3D reconstruction of industrial building elements, including roof panels, floor, rafters, purlins, and columns, from unstructured point clouds. The proposed approach integrates orientation-based filtering, projection onto characteristic planes, morphological analysis, and optimization-based I-profile fitting to generate accurate 3D models. The workflow begins with point cloud preprocessing, where the data are aligned with the building axes and cleaned of outliers, followed by subdivision into two subsets based on local surface orientation. Binary projections are then processed to extract element contours, while roof slopes and panel inclinations are automatically estimated to guide the reconstruction of rafters and purlins. The method was validated on a real-case study of 930 m² industrial warehouse scanned with a mobile laser scanner, resulting in a raw dataset of seven million points. The segmentation achieved F1-scores above 0.90 for floors, roof panels, rafters, and columns, and 0.75 for purlins. Profile fitting yielded an average width error of 3.8%, confirming the robustness and reliability of the reconstruction across diverse structural components.
Abstract. In recent years, the demand for 3D city model development has grown, as demonstrated by initiatives such as Project PLATEAU in Japan. In the construction of LoD2 building models, which are an essential component of 3D city models, the reconstruction of 3D roof models still heavily depends on manual work. To enhance productivity through automation, this study proposes a novel method for automatically reconstructing high-accuracy 3D roof models using orthophotos and Digital Surface Models (DSMs) derived from aerial imagery. In the proposed method, a deep-learning-based model is first applied to orthophotos and DSMs to extract 2D rooflines. Then, the extracted 2D rooflines are refined and polygonised to assemble 2D roof models. Finally, planar fitting was performed on the point cloud generated from the DSM within each 2D roof plane to reconstruct 3D roof models. In this process, the horizontal alignment of rooflines and the continuity between adjacent roof planes were preserved. In the experiments, 3D roof models manually digitized by stereoscopic measurement were used as the ground truth, and the automatically reconstructed 3D roof models were evaluated by comparison with this reference. As a result, the recall values for 2D and 3D roof planes were 0.686 and 0.430, respectively, and increased to 0.723 and 0.455 for roof planes larger than 4 m².
Yongheng Li, Masaya Shimasaki, M. Sakamoto et al.· The International Archives o...· 0 citations
Abstract. This paper presents a semi-automated pipeline for extracting architectural plans from terrestrial LiDAR point clouds of archaeological sites characterized by irregular geometries and significant surface degradation. The proposed workflow converts dense three-dimensional data into simplified two-dimensional representations by combining geometric alignment, expert-guided cross-section selection, feature detection using Intrinsic Shape Signatures (ISS), region-based segmentation, and polyline simplification. The method is specifically designed to handle rock-cut tomb environments, where erosion, noise, and non-planar surfaces complicate conventional Scan-to-Plan approaches. The pipeline is evaluated on six tombs from the Sheikh Said necropolis in Middle Egypt, covering a range of architectural configurations and preservation states. Results demonstrate that the method efficiently produces CAD-compatible outlines that capture the dominant structural geometry while significantly reducing manual drafting time. However, the accuracy of the generated plans depends on surface conditions, with degraded or ornamented areas introducing geometric artifacts that require expert refinement. The proposed approach provides a robust geometric baseline for archaeological documentation and highlights the potential of human-in-the-loop workflows for complex heritage environments.
Marianna Bartrick-Krana, Roberto de Lima-Hernandez, A. Vandesande et al.· The International Archives o...· 0 citations
The results demonstrate the potential of hybrid AI and geometric approaches to improve the efficiency, repeatability, and reliability of Scan-to-BIM processes for historical masonry bridge heritage and show that the geometric quality of the HBIM model depends primarily on the density, spatial distribution and completeness of the structural points, rather than on their total number.
V. Alfio, Massimiliano Pepe, Donato Palumbo et al.· Applied Sciences· 0 citations
With the development of intelligent unmanned systems, it is important for indoor mobile mapping and structural perception to reconstruct building structures in a timely manner from sequential LiDAR point clouds. However, many existing reconstruction methods rely on complete or accumulated point clouds, making them less suitable for partial observations, occlusions, and continuous updates. This paper proposes an incremental geometric reconstruction framework for building structures based on LiDAR point clouds. The method combines temporal state inheritance and orthogonal projection to transform 3D point-cloud processing into 2D plane-based contour updating. A transmissive relationship-based hole detection strategy is introduced to preserve real openings such as doors and windows while completing partially unobserved regions. Simulation and real-world experiments show that the proposed method can recover major planar building structures. In the simulation scene, the proposed method achieves a CD-L1 of 0.088 m, a CD-L2 of 0.007 m2, and an F1-score of 0.901, with an average single-frame processing time of 1.02 s. The experimental results indicate that the proposed method provides a compact and interpretable plane-based structural representation for near-real-time incremental reconstruction of building structures from sequential LiDAR point clouds.
Xian Cao, Changyu Qian, Hanqiang Deng et al.· ISPRS Int. J. Geo Inf.· 0 citations
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.
B. Xiao, Wei Xuan, Jinsong Gao et al.· Symmetry· 0 citations
Open-pit mines contain rapidly changing terrain, discontinuous bench structures, and mixed artificial–natural objects, which complicate automated three-dimensional mapping. This study presents a dual-module workflow for UAV LiDAR point clouds. Module A characterizes local geometry using normal and curvature descriptors, constructs local plane support through RANSAC fitting, and detects candidate bench-line points using an angular-gap criterion, followed by regional grouping and Kalman-filter refinement. Qualitative overlay with the orthophoto showed coherent correspondence with principal platform–slope transitions. Module B segments buildings, roads, and vegetation using a PointNet++ network enhanced by local Transformer self-attention and inverted residual feature transformation. Under a fixed spatial hold-out setting, the network achieved an overall accuracy of 97.6% and a mean intersection over union of 96.4%. It obtained the highest overall accuracy, mean intersection over union, and class-wise intersection over union among the selected baselines, whereas Point Transformer achieved a slightly higher mean class accuracy. The two independently operated modules provide complementary structural and semantic information for open-pit mine mapping. Broader applicability requires reference-based bench-line assessment and evaluation across additional mines and survey periods.
