3D Building Reconstruction Research Articles

Enhanced TomoSAR imaging method with complex least squares for 3D building reconstruction

ABSTRACT Synthetic aperture radar tomography (TomoSAR) has emerged as an advanced technology for the rapid acquisition of three-dimensional information, with model solutions dependent on a specific complex least squares adjustment criterion. We design two TomoSAR imaging algorithms based on two adjustment criterions minimizing the square sum of the real and imaginary components of observation vector residual, and minimizing the square sum of the L2-norm of observation vector residual. Additionally, we propose a strong scatterer recognition method that combines amplitude thresholding and density-based spatial clustering of applications with noise to alleviate the low efficiency and excessive noise in real images. The simulated and practical experiments are conducted to evaluate the performance of algorithms. Results suggested that two algorithms perform similarly in parameter estimation accuracy and noise immunity for buildings with simple structures and single scatterer. However, for buildings with multiple scatterers, the algorithm derived by minimizing the square sum of the L2-norm from the observation vector residual exhibits more robustly than the other algorithm, accurately distinguishing multiple scatterers within pixels and reconstructing 3D scenes mirroring the actual ones. The results verify the effectiveness of the proposed strong scatterer recognition method and the importance of the adjustment criterion in TomoSAR imaging.

3D Building Modelling from ALS Point Clouds by Delaunay Triangulation and Graph Theories

Abstract. As an important task in 3D building reconstruction, 3D roof reconstruction attracts increasing attention. Existing methods have the issue of additional errors caused by multi-step processes, resulting in relatively high uncertainty and potentially affecting the reconstruction accuracy. Deep learning-based methods to achieve the direct extraction of roof vertices and edges for reconstructing 3D roof structures tackle the issue of additional errors while leading to another problem: the reliance on large labeled datasets for training. In this study, a fully rule-based method is proposed to achieve automatic 3D roof reconstruction. Roof vertices with their edges parallel to the x-y plane are first extracted from the point clouds, and subsequently, the left roof edges connecting vertices are inferred by using Delaunay triangulation. Finally, the 3D roof structure is reconstructed by using graph analysis based on the information of roof vertices and edges. This method simplifies the process of 3D roof reconstruction, and the experiment results demonstrate that the proposed method can effectively reconstruct 3D roof structures from point clouds.

Segmentation-aware prior assisted joint global information aggregated 3D building reconstruction

Segmentation-aware prior assisted joint global information aggregated 3D building reconstruction

Automatic Detection and 3D Reconstruction of Buildings from Historical Maps

ABSTRACT This paper presents an automatic 3D building reconstruction methodology for historical urban maps. It uses facade and openings detection on the maps, followed by rectification, regularization, and 3D model generation techniques. Evaluation metrics confirm the effectiveness of the approach, with high accuracy in detecting facades and their openings while maintaining geometric integrity. The flexibility and interoperability of the chosen 3D building representation method allow for adjustments in dimensions without compromising layout, making it suitable for completing the urban environments where facades may not be directly visible. This methodology represents a significant step toward automating the reconstruction of 3D historical urban landscapes, contributing to heritage preservation and architectural understanding.

Compound 3D building modeling with structure-aware partition and primitive assembly from airborne laser scanning point clouds

ABSTRACT Urban digital twins and realistic three-dimensional (3D) scenes have further enhanced the ever-increasing demand for building models. Airborne Laser Scanning (ALS) point clouds are the predominant data source for 3D building reconstruction owing to their highly detailed spatial features. However, information on the reconstruction of compound buildings (i.e. buildings with diverse plane structures or various roof structures) is lacking. Existing methods often produce building models that suffer from topological inconsistencies and/or geometric errors. To address these issues, this study proposes an automatic building reconstruction approach based on ALS point cloud that offers both modeling flexibility and geometric consistency. Specifically, a structure-aware partitioning algorithm that partitions a complex building roof into several regular roof patches is incorporated. Subsequently, a primitive model library comprising representative primitives suitable for building reconstruction is created. Suitable primitive model selection and reconstruction optimization are employed to ensure the accuracy and compactness in the final model. To comprehensively evaluate the performance, two typical ALS point cloud datasets are tested. Experiments demonstrate the generated models can achieve a boundary consistency of 92% while ensuring Root Mean Square Error below 0.09 m. Comparative experiments with state-of-the-art methods further validate the effectiveness of the proposed approach in compound building reconstruction.

Automatic Design Line Detection in Urban Building Images through DCT

The conversion of urban building images into design lines is a valuable technique used in architecture. It aids in theanalysis of design styles and building components. Recent studies have shown a significant interest in usingcomputational methods to examine the design lines in architectural images, such as plans, facades, and streetscapes.This research presents an automated approach that utilizes kernel filters to extract edges and reduce noise fromvarious architectural images. Additionally, it introduces a new filter that separates lines based on their directionsutilizing the Discrete Cosine Transform (DCT). The proposed technique generates distinct images that display thevertical, horizontal, and curved lines extracted from the original images. The results demonstrate that the proposedtechnique is efficient not only with architectural drawings but also with photographs of existing buildings. Thistechnique opens the door for further experimentation in artificial intelligence, computational aesthetics, imagerectification and calibration, and 3D building reconstruction.

Semantic 3D reconstruction-oriented image dataset for building component segmentation

In image-driven 3D building reconstruction, instance segmentation is fundamental to pixel-wise building component detection, which can be fused with 3D data like point clouds and meshes via camera projection for semantic reconstruction. While deep learning-based segmentation has obtained promising results, it relies heavily on large-scale datasets for training. Unfortunately, existing large-scale image datasets often include irrelevant objects that obstruct building components, making them unsuitable for 3D building reconstruction. This paper addresses this gap by introducing a large-scale building image dataset to facilitate building component segmentation for 3D reconstruction. The dataset comprises 3378 images captured from both interiors and exteriors of 36 university buildings, annotated with 49,380 object instances across 11 classes. Rigorous quality control measures were employed during data collection and annotation. Evaluation of five typical deep learning-based instance segmentation models demonstrates the dataset's suitability for training and its value as a benchmark dataset for building component segmentation.

Research on the Reconstruction Method of Old Houses in Mindong, Republic of China, Based on a Wearable Mobile Scanning System

To address the complex structures of historical buildings in Mindong, lack of historical reference materials, and heavy workload of traditional surveying and mapping methods in the field, a 3D reconstruction method of historical building based on a wearable mobile scanning system for data acquisition was studied. First, a wearable mobile scanning system is used to scan historical buildings in three dimensions. The data are fused to obtain high-precision three-dimensional point cloud data of historical buildings. Second, based on the processed point cloud, a 2D map of historical buildings is accurately drawn using point cloud slicing. Finally, three-dimensional reconstruction of historical buildings is realized using a 2D atlas of historical buildings and modern modeling technology. The accuracy of the three-dimensional reconstruction model was analyzed using a fitting algorithm and structural geometric relationship to verify the effectiveness and accuracy of the method. An old house in Mindong, Republic of China, was taken as the research object. Experimental analysis revealed that (1) a wearable mobile scanning system is suitable for high-quality point cloud data acquisition of buildings with complex geometric features, solving the problems of low efficiency and poor coverage of traditional surveying and mapping results; and (2) the method realizes 2D results rendering and 3D reconstruction of historical buildings based on the wearable mobile scanning system data with good accuracy, providing a reference for the protection and repair of historical buildings and health assessment.

3D Reconstruction of Buildings Based on 3D Gaussian Splatting

3D Reconstruction of Buildings Based on 3D Gaussian Splatting

3D Reconstruction of Ancient Buildings Using UAV Images and Neural Radiation Field with Depth Supervision

The 3D reconstruction of ancient buildings through inclined photogrammetry finds a wide range of applications in surveying, visualization and heritage conservation. Unlike indoor objects, reconstructing ancient buildings presents unique challenges, including the slow speed of 3D reconstruction using traditional methods, the complex textures of ancient structures and geometric issues caused by repeated textures. Additionally, there is a hash conflict problem when rendering outdoor scenes using neural radiation fields. To address these challenges, this paper proposes a 3D reconstruction method based on depth-supervised neural radiation fields. To enhance the representation of the geometric neural network, the addition of a truncated signed distance function (TSDF) supplements the existing signed distance function (SDF). Furthermore, the neural network’s training is supervised using depth information, leading to improved geometric accuracy in the reconstruction model through depth data obtained from sparse point clouds. This study also introduces a progressive training strategy to mitigate hash conflicts, allowing the hash table to express important details more effectively while reducing feature overlap. The experimental results demonstrate that our method, under the same number of iterations, produces images with clearer structural details, resulting in an average 15% increase in the Peak Signal-to-Noise Ratio (PSNR) value and a 10% increase in the Structural Similarity Index Measure (SSIM) value. Moreover, our reconstruction model produces higher-quality surface models, enabling the fast and highly geometrically accurate 3D reconstruction of ancient buildings.

PU-CTG: A Point Cloud Upsampling Network Using Transformer Fusion and GRU Correction

Point clouds are widely used in remote sensing applications, e.g., 3D object classification, semantic segmentation, and building reconstruction. Generating dense and uniformly distributed point clouds from low-density ones is beneficial to 3D point cloud applications. The traditional methods mainly focus on the global shape of 3D point clouds, thus ignoring detailed representations. The enhancement of detailed features is conducive to generating dense and uniform point clouds. In this paper, we propose a point cloud upsampling network to improve the detail construction ability, named PU-CTG. The proposed method is implemented by a cross-transformer-fused module and a GRU-corrected module. The aim of the cross-transformer module is to enable the interaction and effective fusion between different scales of features so that the network can capture finer features. The purpose of the gated recurrent unit (GRU) is to reconstruct fine-grained features by rectifying the feedback error. The experimental results demonstrate the effectiveness of our method. Furthermore, the ModelNet40 dataset is upsampled by PU-CTG, and the classification experiment is applied to PointNet to verify the promotion ability of this network.

3D Urban Building Reconstruction through Neural Rendering and UAV Imagery

3D Urban Building Reconstruction through Neural Rendering and UAV Imagery

Retracted: 3D Reconstruction and Intelligent Digital Conservation of Ancient Buildings Based on Laser Point Cloud Data

Retracted: 3D Reconstruction and Intelligent Digital Conservation of Ancient Buildings Based on Laser Point Cloud Data

Completing point clouds using structural constraints for large-scale points absence in 3D building reconstruction

The completion of point cloud directly affects the accuracy of primitive parameter extraction and 3D reconstruction. Due to the limitations of sensor scanning, point cloud are often incomplete due to occlusions during the data collection. To solve the problem of incomplete building point clouds and to support geometric detail LoD2 reconstruction, a point cloud completion method with structural constraint is proposed in this paper. First, based on the idea of cloth simulation, regularity and planarity of the building were used to impose structural constraints on the cloth nodes. Combined with the rigidity of the building, the force rules of nodes under the distribution of the building structure are formulated. Then, the sinking and rebounding stages of the node were simulated to recover the position of point cloud in the area of interest. Finally, the missing surface in each façade direction was completed by attitude adjustment. The solution of a multi-layer structural façade was realized by the selection of parameters during the sinking and rebounding stage. The feasibility and accuracy of the proposed point cloud completion method have been verified through experiments. It is demonstrated that the proposed method can improve the integrity of a building point cloud by achieving more than 90% coverage. Compared with existing methods, the proposed method can deal with the problem of large-scale structure missing from buildings with fewer limitations. The patched points do not rely on the geometric primitives’ extraction and are based on the distribution of existing points without redundant observations, so the patched points adapt better to the existing building points. The proposed method has enhanced the utilization of point clouds and improved the detail of LoD2 reconstruction. It provides a new feasible method for point cloud completion. The code of the method is available at https://github.com/bufanzhao/point-cloud-completion.git.

Precise plane registration with multiple geometric feature matching and weighted least squares estimation

Point cloud registration is a fundamental problem for 3D laser scanning technology, which is extensively applied in geographic entity modelling such as 3D reconstruction of urban roads and buildings. Registration accuracy is one of the main focuses for these applications. However, noisy points, limited overlap, varying data sources, and differing measuring accuracy may cause changes between point cloud sets and reduce registration accuracy. This paper introduces an automatic plane registration method for urban roads and building scenes, which does not need manual on-site deployment. Firstly, plane primitives are extracted using voxel-based filtering region growth. Next, corresponding planes for the extracted primitives are identified by leveraging saliency features and constructing adjacency matrices. Finally, plane registration is achieved using a weighted plane coordinate conversion model. Through real-world scene experimentation, an overall accuracy of 10 cm and a segmental registration accuracy of 5–6 cm is achieved with our method, outperforming both feature point-based and global point cloud registration approaches in terms of efficiency and accuracy.

3D Visual Reconstruction as Prior Information for First Responder Localization and Visualization.

In professional use cases like police or fire brigade missions, coordinated and systematic force management is crucial for achieving operational success during intervention by the emergency personnel. A real-time situation picture enhances the coordination of the team. This situation picture includes not only an overview of the environment but also the positions, i.e., localization, of the emergency forces. The overview of the environment can be obtained either from known situation pictures like floorplans or by scanning the environment with the aid of visual sensors. The self-localization problem can be solved outdoors using the Global Navigation Satellite System (GNSS), but it is not fully solved indoors, where the GNSS signal might not be received or might be degraded. In this paper, we propose a novel combination of an inertial localization technique based on simultaneous localization and mapping (SLAM) with 3D building scans, which are used as prior information, for geo-referencing the positions, obtaining a situation picture, and finally visualizing the results with an appropriate visualization tool. We developed a new method for converting point clouds into a hexagonal prism map specifically designed for our SLAM algorithm. With this combination, we could keep the equipment for first responders as lightweight as required. We showed that the positioning led to an average accuracy of less than 1m indoors, and the final visualization including the building layout obtained by the 3D building reconstruction will be advantageous for coordinating first responder operations.

Interactive piecewise planar building reconstruction from a single image based on geometric priors

The development of methods to reconstruct the piecewise planar structures of buildings from a single image is an important and challenging problem in the field of computer vision. Although most prior works have considered fully automatic reconstruction solutions, these methods typically perform poorly for complex building structures. To address this problem, we propose an interactive single-image 3D building reconstruction method to integrate automatic plane inference with interactive plane refinement based on geometric priors. In this method, based on geometric priors (e.g., the orientation of the plane and the intersection angle between planes) learned using convolutional neural networks, building regions are first partitioned into multiple polygonal regions using click interactions. Then, the planes corresponding to these polygonal regions are automatically and progressively inferred by taking full advantage of the constraints constructed using the geometric priors. Finally, under the guidance of interactive plane refinement based on click correlations, the resulting planes are globally optimized by jointly utilizing image cues and geometric priors. The results of an experimental evaluation on three datasets demonstrate that the proposed method achieved better performance than existing methods in terms of both qualitative and quantitative measures.

Machine learning-based segmentation of aerial LiDAR point cloud data on building roof

ABSTRACT Three-dimensional (3D) reconstruction of a building can be facilitated by correctly segmenting different feature points (e.g. in the form of boundary, fold edge, and planar points) over the building roof, and then, establishing relationships among the constructed feature lines and planar patches using the segmented points. Present machine learning-based segmentation approaches of Light Detection and Ranging (LiDAR) point cloud data are confined only to different object classes or semantic labelling. In the context of fine-grained feature point classification over the extracted building roof, machine learning approaches have not yet been explored. In this paper, after generating the ground truth data for the extracted building roofs from three different datasets, we apply machine learning methods to segment the roof point cloud based on seven different effective geometric features. The goal is not to semantically enhance the point cloud, but rather to facilitate the application of 3D building reconstruction algorithms, making them easier to use. The calculated F1-scores for each class confirm the competitive performances over the state-of-the-art techniques, which are more than 95% almost in each area of the used datasets.

Semantic-guided 3D building reconstruction from triangle meshes

Planar primitives tend to be incorrectly detected or incomplete in complex scenes where adhesions exist between different objects, resulting in topology errors in the reconstructed models. We propose a semantic-guided building reconstruction method known as semantic-guided reconstruction (SGR), which is capable of achieving the independence and integrity of building models in two key stages. In the first stage, the space partition is represented by a 2.5D convex cell complex and is capable of restoring planar primitives that are easily lost and can further infer the potential structural adaptivity. The second stage incorporates semantic information into a graph-cut formulation that can assist in the independent reconstruction of buildings while eliminating interference from the surrounding environment. Our experimental results confirmed that the SGR method can authentically reconstruct weakly observed surfaces. Furthermore, qualitative and quantitative evaluations show that SGR is suitable for reconstructing surfaces from insufficient data with semantic and geometric ambiguity or semantic errors and can obtain watertight models considering fidelity, integrity and time complexity.

Digital reconstructions of picture galleries as art historical method: The virtual museum at the Royal Palace in Stockholm

We are now witnessing a wave of research using digital tools to create 3D reconstructions of buildings, exhibitions, and objects. We would therefore like to critically discuss the scholarly value of reconstructions. What are we learning? Which problems are solved? What new knowledge can be gained? These are questions posed from a background of history of display and a pilot study in which we are reconstructing two hangings in a gallery at the Royal Palace in Stockholm. We conclude that an immersive 3D reconstruction can give new insights into narratives and hierarchies of art displays. Our model, made with the game engine Unity and the software Virtual Museum, allows us to show and analyze historical changes and developments as well as aspects as eye-lines, visibility and visitors flow to a comparably low cost. This way an immersive 3D-reconstruction can be used not only for pedagogical visualizations, but become an effective research tool.