Surface reconstruction by parallel and unified particle-based resampling from point clouds

In this paper, a method of reconstructing 3D (three dimensional) models from the original scanned point cloud using priori templates is proposed. Different from previous reconstruction methods that triangulate and fit the original scanning point cloud directly, we construct a priori template based on the CAD (computer aided design) model and guide the reconstruction of the original scanning point cloud with the priori template. Given a CAD model, the basic geometric elements are used as the basic units to extract the set elements of 3D shapes. Then the geometric elements are meshed, and the normal vectors at the mesh nodes are extracted. The corresponding point cloud data of each basic element are extracted from the original point cloud. The point cloud data near the normal of the guide point are searched, and the Gaussian weighted average value of the searched point represents the actual geometric parameters of the part at the guide point. Finally, the geometric elements of the basic unit are reconstructed locally by Non-Uniform Rational B-Splines surface fitting, and the complete reconstruction model is obtained by integrating the local reconstruction. Experiments show that our method can solve the problems of high quality reconstruction, sharp feature preservation, and detail recovery in surface reconstruction.

Integrated gradients is an explainable AI technique that aims to explain the relationship between a model’s predictions in terms of its features. Adapting this technique to point clouds and semantic segmentation models allows a class-wise attribution of the predictions with respect to the input features. This allows better insight into how a model reached a prediction. Furthermore, it allows a quantitative analysis of how much each feature contributes to a prediction. To obtain these attributions, a baseline with high entropy is generated and interpolated with the point cloud to be visualized. These interpolated point clouds are then run through the network and their gradients are collected. By observing the change in gradients during each iteration an attribution can be found for each input feature. These can then be projected back onto the original point cloud and compared to the predictions and input point cloud. These attributions are generated using RandLA-Net due to it being an efficient semantic segmentation model that uses comparatively few parameters, therefore keeping the number of gradients that must be stored at a reasonable level. The attribution was run on the public Semantic3D dataset and the SVGEO large-scale urban dataset.

Surface reconstruction from point clouds has been a well-studied research topic with applications in computer vision and computer graphics. Recently, several learningbased methods were proposed for 3D shape representation through implicit functions which among others can be used for point cloud-based reconstruction. Although delivering compelling results for synthetic object datasets of overseeable size, they fail to represent larger scenes accurately, presumably due to the use of only one global latent code for encoding an entire scene or object. We propose to encode only parts of objects with features attached to unstructured point clouds. To this end we use a hierarchical feature map in 3D space, extracted from the input point clouds, with which local latent shape encodings can be queried at arbitrary positions. We use a permutohedral lattice to process the hierarchical feature maps sparsely and efficiently. This enables accurate and detailed point cloud-based reconstructions for large amounts of points in a time-efficient manner, showing good generalization capabilities across different datasets. Experiments on synthetic and real world datasets demonstrate the reconstruction capability of our method and compare favorably to state-of-the-art methods.

We propose a level set-based semi-Lagrangian method on graded adaptive Cartesian grids to address the problem of surface reconstruction from point clouds. The goal is to obtain an implicit, high-quality representation of real shapes that can subsequently serve as computational domain for partial differential equation models. The mathematical formulation is variational, incorporating a curvature constraint that minimizes the surface area while being weighted by the distance of the reconstructed surface from the input point cloud. Within the level set framework, this problem is reformulated as an advection–diffusion equation, which we solve using a semi-Lagrangian scheme coupled with a local high-order interpolator. Building on the features of the level set and semi-Lagrangian method, we use quadtree and octree data structures to represent the grid and generate a mesh with the finest resolution near the zero level set and the point cloud data. The complete surface reconstruction workflow is described, including localization and reinitialization techniques, as well as strategies to handle complex and evolving topologies. A broad set of numerical tests in two and three dimensions is presented to assess the effectiveness of the method.

Skeleton-based intrinsic symmetry detection on point clouds

The contours, one of the most significant human perceptual features, have a significant impact on point cloud processing. In urban scenes, contour extraction is quite challenging due to the enormous number of unstructured and irregular points (typically greater than 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">7</sup> points). In this paper, we propose a Large-scale 3D point cloud Contour Extraction Network (LCE-NET) to generate contours consistent with human perception of outdoor scenes. To our knowledge, it is the first time that an end-to-end learning-based framework has been proposed for contour extraction on point cloud at this scale. The proposed LCE-Net is essentially a two-phase system. In the first phase, potential vertexes are detected from the input point cloud by the vertex detection module, then in the second phase, a designed overcomplete line proposal set is generated, and invalid line segments are further suppressed by the line proposal discrimination module. The two phases are jointly trained by a uniform loss function to promote the information interchange, thus leading to extraction results with satisfied accurate and false alarm ratings. Since there is hardly any available dataset with labeled contours for the large-scale outdoor scene, we open sourced SemanticLine, the first dataset for large-scale point clouds with labeled contour information, based on re-annotation of previous mapping level point cloud dataset semantic3D. Experimental results demonstrate that LCE-NET can effectively extract parametric contour lines from large-scale point clouds of urban scenes. Additionally, it outperforms the state-of-the-art approaches. The code will be open source on GitHub soon.

Self-supervised rigid transformation equivariance for accurate 3D point cloud registration

Introduction and aimsIntraoral scanning (IOS) captures real-time surface morphology of teeth and is widely used in clinical dentistry. However, due to the complex intraoral environment, data loss during scanning is common, leading to incomplete three-dimensional (3D) point clouds. This study aimed to develop and evaluate a deep learning–based method to automatically restore missing regions in intraoral 3D point clouds, thereby improving the accuracy and efficiency of digital orthodontic workflows.MethodsA Point Fractal Network architecture was adopted to reconstruct incomplete IOS data. A dataset comprising 314 IOS scans and 4162 individual teeth was used for training and validation. Missing data were simulated by removing random portions of point clouds (5%, 10%, 15%, and 20%). Model performance was assessed using Chamfer distance (CD) to measure the accuracy of point cloud completion across different levels of data loss.ResultsThe proposed method achieves robust performance, maintaining average CD values below 0.01 across most levels of simulated data loss. Visual comparisons confirmed high geometric fidelity between the completed and original point clouds. Furthermore, the model demonstrated efficient processing, completing each point cloud in approximately 0.5 seconds, enabling near real-time restoration during clinical scanning.ConclusionThe deep learning–based model accurately restores missing IOS data, improving the precision and efficiency of digital dental workflows. Its speed and accuracy support real-time clinical applications and reduce reliance on manual corrections.Clinical RelevanceThis method improves clinical efficiency, reduces chairside time, and enhances both patient comfort and treatment acceptance. In addition, it minimises human error and increases the precision of dental restorations. As digital dentistry continues to evolve, this approach holds great potential for improving the accuracy and efficiency of dental treatments, paving the way for broader artificial intelligence integration in clinical practice.

With the rapid development of smart cities, intelligent navigation, and autonomous driving, how to quickly obtain 3D spatial information of urban buildings and build a high-precision 3D fine model has become a key problem to be solved. As the two-dimensional mapping results have constrained various needs in people’s social life, coupled with the concept of digital city and advocacy, making three-dimensional, virtualization and actualization become the common pursuit of people’s goals. However, the original point cloud obtained is always incomplete due to reasons such as occlusion during acquisition and data density decreasing with distance, resulting in extracted boundaries that are often incomplete as well. In this paper, based on the study of current mainstream 3D model data organization methods, geographic grids and map service specifications, and other related technologies, an intelligent urban 3D modeling model based on multisource data point cloud algorithm is designed for the two problems of unified organization and expression of urban multisource 3D model data. A point cloud preprocessing process is also designed: point cloud noise reduction and downsampling to ensure the original point cloud geometry structure remain unchanged, while improving the point cloud quality and reducing the number of point clouds. By outputting to a common 3D format, the 3D model constructed in this paper can be applied to many fields such as urban planning and design, architectural landscape design, urban management, emergency disaster relief, environmental protection, and virtual tourism.

In the current methods of point cloud processing, there are still several limitations, particularly in achieving high precision and accuracy for large objects in complex environments. Existing techniques often struggle with incomplete or noisy data, leading to inaccurate contour extraction. In view of the challenges associated with the sparse and discrete nature of point clouds in complex environments, which lead to poor accuracy and stability in object contour extraction, this paper proposes a novel method for accurately extracting the contours of three-dimensional target point clouds. The method integrates high-resolution images with sparse point cloud information to address these issues. Firstly, the local characteristics of the point cloud are calculated, allowing for the selection of a contour point cloud. Next, depth information from two-dimensional images is obtained through a fuzzy mapping relationship. Finally, constraint conditions are established to derive a more accurate predicted value of the contour point cloud. Experiments demonstrate that the proposed method effectively improves the precision and accuracy of contour extraction for large objects, reducing measurement deviation by approximately 64.9% compared to using the original point cloud alone. Additionally, the method shows a more accurate completion effect on parts of the contour that are missing, underscoring its robustness and effectiveness in challenging scenarios.

Abstract. Laser scanning samples the surface geometry of objects efficiently and records versatile information as point clouds. However, often more scans are required to fully cover a scene. Therefore, a registration step is required that transforms the different scans into a common coordinate system. The registration of point clouds is usually conducted in two steps, i.e. coarse registration followed by fine registration. In this study an automatic marker-free coarse registration method for pair-wise scans is presented. First the two input point clouds are re-sampled as voxels and dimensionality features of the voxels are determined by principal component analysis (PCA). Then voxel cells with the same dimensionality are clustered. Next, the Extended Gaussian Image (EGI) descriptor of those voxel clusters are constructed using significant eigenvectors of each voxel in the cluster. Correspondences between clusters in source and target data are obtained according to the similarity between their EGI descriptors. The random sampling consensus (RANSAC) algorithm is employed to remove outlying correspondences until a coarse alignment is obtained. If necessary, a fine registration is performed in a final step. This new method is illustrated on scan data sampling two indoor scenarios. The results of the tests are evaluated by computing the point to point distance between the two input point clouds. The presented two tests resulted in mean distances of 7.6 mm and 9.5 mm respectively, which are adequate for fine registration.

Surface reconstruction is a challenging task when input point clouds, especially real scans, are noisy and lack normals. Observing that the Multilayer Perceptron (MLP) and the implicit moving least-square function (IMLS) provide a dual representation of the underlying surface, we introduce Neural-IMLS, a novel approach that directly learns a noise-resistant signed distance function (SDF) from unoriented raw point clouds in a self-supervised manner. In particular, IMLS regularizes MLP by providing estimated SDFs near the surface and helps enhance its ability to represent geometric details and sharp features, while MLP regularizes IMLS by providing estimated normals. We prove that at convergence, our neural network produces a faithful SDF whose zero-level set approximates the underlying surface due to the mutual learning mechanism between the MLP and the IMLS. Extensive experiments on various benchmarks, including synthetic and real scans, show that Neural-IMLS can reconstruct faithful shapes even with noise and missing parts. The source code can be found at https://github.com/bearprin/Neural-IMLS.

Given an input point cloud P in ℜ3, this paper proposes a novel algorithm to identify surface neighbors of each point p∈P respecting the underlying surface S and then to construct a piecewise linear surface for P. The algorithm utilizes the simple k-nearest neighborhood in constructing local surfaces. It makes use of two concepts: a local convexity criterion to extract a set of surface neighbors for each point, and a global projection test to determine an order for the reconstruction. Our algorithm not only produces a topologically correct surface for well-sampled point sets, but also adapts well to handle under-sampled point sets. Furthermore, the computational cost of the algorithm increases almost linearly in the size of the point cloud. It, thus, scales well to deal with large input point sets.

Visual enhancement of 3D images of rock faces for fracture mapping

Chimneys are architectural elements of difficult access and analysis in heritage buildings. This paper presents a method for automatic modelling of round brick chimneys and analysing their inclination, straightness and surface. The method uses as input data point clouds acquired with a Terrestrial Laser Scanner. Four chimneys have been surveyed on the north face of Bragança Dukes’ Palace in Guimarães, Portugal. The method consists of two main processes. First, the point cloud of each chimney is segmented into circumferential sections and adjusted to cylinders by applying Maximum Likelihood Sample Consensus. From the set of centroids, the inclination and the straightness of the chimney is estimated. Second, the point cloud chimney is segmented longitudinally and adjusted to finite planes. The distance estimation between the input point cloud and the modelled planes allows detecting the lack of bricks or mortar erosions. The proposed method allows estimating characteristics in chimneys even if the chimneys have not been completely acquired.