Geometry Reconstruction Research Articles

Machine Learning and Deep Learning for the Built Heritage Analysis: Laser Scanning and UAV-Based Surveying Applications on a Complex Spatial Grid Structure

The reconstruction of 3D geometries starting from reality-based data is challenging and time-consuming due to the difficulties involved in modeling existing structures and the complex nature of built heritage. This paper presents a methodological approach for the automated segmentation and classification of surveying outputs to improve the interpretation and building information modeling from laser scanning and photogrammetric data. The research focused on the surveying of reticular, space grid structures of the late 19th–20th–21st centuries, as part of our architectural heritage, which might require monitoring maintenance activities, and relied on artificial intelligence (machine learning and deep learning) for: (i) the classification of 3D architectural components at multiple levels of detail and (ii) automated masking in standard photogrammetric processing. Focusing on the case study of the grid structure in steel named La Vela in Bologna, the work raises many critical issues in space grid structures in terms of data accuracy, geometric and spatial complexity, semantic classification, and component recognition.

Three-Dimensional Geometry Reconstruction Method from Multi-View ISAR Images Utilizing Deep Learning

The three-dimensional (3D) geometry reconstruction method utilizing ISAR image sequence energy accumulation (ISEA) shows great performance on triaxial stabilized space targets but fails when there is unknown motion from the target itself. The orthogonal factorization method (OFM) can solve this problem well under certain assumptions. However, due to the sparsity and anisotropy of ISAR images, the extraction and association of feature points become very complicated, resulting in the reconstructed geometry usually being a relatively sparse point cloud. Therefore, combining the advantages of the above methods, an extended factorization framework (EFF) is proposed. First, the instance segmentation method based on deep learning is used for the extraction and association of a number of key points on multi-view ISAR images. Then, the projection vectors between the 3-D geometry of the space target and the multi-view ISAR images are obtained, using the improved factorization method. Finally, the 3D geometry reconstruction problem is transformed into an unconstrained optimization problem and solved via the quantum-behaved particle swarm optimization (QPSO) method. The proposed framework uses discretely observed multi-view range–Doppler ISAR images as an input, which can make full use of the long-term data of space targets from multiple perspectives and which is non-sensitive to movement. Therefore, the proposed framework shows high feasibility in practical applications. Experiments on simulated and measured data show the effectiveness and robustness of the proposed framework.

Multiscale Design of Graded Stochastic Cellular Structures for the Heat Transfer Problem

Advancesin additive manufacturing technology have expanded the development prospect of structures with complex configurations. Cellular structures have been a hot research topic in recent years for their superior performance and characteristics, such as being lightweight and having high specific strength and good permeability. With a high specific surface area, cellular structures perform noticeably well in heat transfer applications when subjected to a body heat source. In this paper, a scale-separated multiscale design of theVoronoi graded stochastic cellular structure (Voronoi-GSCS) that considers the heat transfer problem is proposed. The design method is composed of three steps: the offline calculation on the microscale, the online optimization on the macroscale, and geometry reconstruction on the full scale. Numerical examples are given to show the effectiveness and superiority of the developed method for designing the Voronoi-GSCS. The results obtained by the solid isotropic material with penalization (SIMP) approach are used for comparison. The size effect analysis was conducted to research the influence of the size of the microstructure on the Voronoi-GSCS. It should be stressed that the smallest struts were larger than the minimum print size of the additive manufacturing so that the Voronoi-GSCS could be conveniently exploited in heat transfer applications.

Workflow Comparison for Combined 4D MRI/CFD Patient-Specific Cardiovascular Flow Simulations of the Thoracic Aorta

AbstractComputational fluid dynamics (CFD) has been widely used to predict and understand cardiovascular flows. However, the accuracy of CFD predictions depends on faithful reconstruction of patient vascular anatomy and accurate patient-specific inlet and outlet boundary conditions. 4-Dimensional magnetic resonance imaging (4D MRI) can provide patient-specific data to obtain the required geometry and time-dependent flow boundary conditions for CFD simulations, and can further be used to validate CFD predictions. This work presents a framework to combine both spatiotemporal 4D MRI data and patient monitoring data with CFD simulation workflows. To assist practitioners, all aspects of the modeling workflow, from geometry reconstruction to results postprocessing, are illustrated and compared using three software packages (ansys, comsol, SimVascular) to predict hemodynamics in the thoracic aorta. A sensitivity analysis with respect to inlet boundary condition is presented. Results highlight the importance of 4D MRI data for improving the accuracy of flow predictions on the ascending aorta and the aortic arch. In contrast, simulation results for the descending aorta are less sensitive to the patient-specific inlet boundary conditions.

Learning the black hole metric from holographic conductivity

We construct a neural network to learn the Reissner-Nordstr\"om-anti--de Sitter black hole metric based on the data of optical conductivity by holography. The linear perturbative equation for the Maxwell field is rewritten in terms of the optical conductivity such that the neural network is constructed based on the discretization of this differential equation. In contrast to all previous models in anti--de Sitter/deep learning duality, the derivative of the metric function appears in the equation of motion and we propose distinct finite difference methods to discretize this function. The notion of the reduced conductivity is also proposed to avoid the divergence of the optical conductivity near the horizon. The dependence of the training outcomes on the location of the cutoff, the temperature as well as the frequency range is investigated in detail. This work provides a concrete example for the reconstruction of the bulk geometry with the given data on the boundary by deep learning.

An All-in-One Tool for 2D Atherosclerotic Disease Assessment and 3D Coronary Artery Reconstruction.

Diagnosis of coronary artery disease is mainly based on invasive imaging modalities such as X-ray angiography, intravascular ultrasound (IVUS) and optical coherence tomography (OCT). Computed tomography coronary angiography (CTCA) is also used as a non-invasive imaging alternative. In this work, we present a novel and unique tool for 3D coronary artery reconstruction and plaque characterization using the abovementioned imaging modalities or their combination. In particular, image processing and deep learning algorithms were employed and validated for the lumen and adventitia borders and plaque characterization at the IVUS and OCT frames. Strut detection is also achieved from the OCT images. Quantitative analysis of the X-ray angiography enables the 3D reconstruction of the lumen geometry and arterial centerline extraction. The fusion of the generated centerline with the results of the OCT or IVUS analysis enables hybrid coronary artery 3D reconstruction, including the plaques and the stent geometry. CTCA image processing using a 3D level set approach allows the reconstruction of the coronary arterial tree, the calcified and non-calcified plaques as well as the detection of the stent location. The modules of the tool were evaluated for efficiency with over 90% agreement of the 3D models with the manual annotations, while a usability assessment using external evaluators demonstrated high usability resulting in a mean System Usability Scale (SUS) score equal to 0.89, classifying the tool as "excellent".

3D bioprinting as a prospective therapeutic strategy for corneal limbal epithelial stem cell deficiency.

Limbal epithelial stem cells (LESCs) are responsible for the maintenance and repair of the corneal surface. Injuries and diseases of the eye may result in a vision condition called limbal stem cell deficiency (LSCD). Without limbal stem cells, the cornea becomes opaque, vascularized, and inflamed. Cultured LESC therapy as a treatment method was first described in 1997, and LESCs cultured from either patients or donors have been used to treat LSCD successfully. However, the main source of cornea for LSCD treatment is from donors, which are too few to meet the demand (less than 1:70 of cases). The global shortage of donor cornea promotes the need for studies exploring corneal limbus alternatives. Many problems still remain unresolved, such as original geometry reconstruction, corneal epithelial regeneration, and ocular optical function restoration. 3D bioprinting has garnered tremendous attention in recent years, and significant advances have been made in fabricating cell-laden scaffolds. These advancements could lead to a promising treatment for LSCD. It is possible that alternative limbus stem cells can be constructed using 3D printing, which, in corneal limbus regeneration, enables personalized corneal implants and fabrication of single- or multilayer corneal limbus equivalents with corneal limbal stem cells. In this review, the progress, applications, and limitations of the most influential works regarding current treatments of LESC deficiency are discussed. The advantages of 3D bioprinting are illustrated, and some first promising steps toward the creation of a functional cornea limbus with 3D bioprinting are discussed. Finally, insights into the prospects and technical challenges facing the future research of 3D bioprinting of corneal limbus alternatives in vivo and in vitro are provided.

Thermal design of functionally graded cellular structures with multiple microstructure configurations through topology optimization

Functionally graded cellular structures (FGCS) have attracted extensive attention in engineering due to their excellent performance and great flexibility. Focusing on thermal applications, this paper proposes a data-driven topology optimization (TO) approach for FGCS with multiple microstructure configurations. The design process is formulated as two distinct phases: lattice configuration determination at the microscale and material distribution at the macroscale. Specifically, a multi-cut level set method that can generate various graded microstructures (GMs) is performed firstly. For each type of GMs, microstructure instances are sampled by varying the relative densities, and the numerical homogenization algorithm is applied to compute their effective thermal conductivities. Then, a spectral decomposition-based interpolation model is constructed to predict the homogenized properties. After the model preparation at the microscale, a density-based TO method is modified to find the optimized macro-distribution of GMs. A multi-material interpolation approach is adopted to achieve the free selection of controllable types of base cells. At the geometry reconstruction stage, a post-processing method is suggested for improving the structural connectivity. Numerical examples and discussions demonstrate the effectiveness and versatility of the proposed design framework.

Annotated computed tomography coronary angiogram images and associated data of normal and diseased arteries

Computed Tomography Coronary Angiography (CTCA) is a non-invasive method to evaluate coronary artery anatomy and disease. CTCA is ideal for geometry reconstruction to create virtual models of coronary arteries. To our knowledge there is no public dataset that includes centrelines and segmentation of the full coronary tree. We provide anonymized CTCA images, voxel-wise annotations and associated data in the form of centrelines, calcification scores and meshes of the coronary lumen in 20 normal and 20 diseased cases. Images were obtained along with patient information with informed, written consent as part of the Coronary Atlas. Cases were classified as normal (zero calcium score with no signs of stenosis) or diseased (confirmed coronary artery disease). Manual voxel-wise segmentations by three experts were combined using majority voting to generate the final annotations. Provided data can be used for a variety of research purposes, such as 3D printing patient-specific models, development and validation of segmentation algorithms, education and training of medical personnel and in-silico analyses such as testing of medical devices.

Computational framework for efficient high-fidelity optimization of bio-inspired propulsion and its application to accelerating swimmers

A new computational framework for high-fidelity optimization of kinematic gaits during self-propelled undulatory swimming is developed. A computational framework utilizes a spectral-element method on moving body-fitted grids for a simulation of self-propelled swimming, and a surrogate-based optimization (SBO) procedure. A new volume-conservation method for reconstruction of a swimmer's geometry during the undulatory motion is proposed to ensure numerical stability of the fluid-structure interaction solver in an incompressible flow framework. A surrogate-based optimization algorithm that utilizes a Kriging response surface method is adopted and further developed in this work to manage the optimization process in the presence of physiological constraints on the fish body motion. A grid convergence of the optimization results is established, and the influence of the polynomial refinement on the results of optimization procedure is assessed. The increase in polynomial order does not change the optimum gaits of locomotion or relative efficiency rankings between the modes, but it results in slightly lower predicted efficiency for all the modes. The optimum solution is characterized by a kinematic gait that generates the reverse Karman vortex street associated with high propulsive efficiency. Efficiency of sub-optimum modes is found to increase with both the tail amplitude and the effective flapping length of the swimmer, and a new scaling law is proposed to capture these trends. Lastly, the SBO algorithm converged to an optimized gate with significantly less function evaluations than typically observed for evolutionary algorithms. This suggests that the SBO framework is a well suited alternative for high-fidelity optimization of fluid and structure problems.

2D-3D reconstruction of the proximal femur from DXA scans: Evaluation of the 3D-Shaper software.

Introduction: Osteoporosis is currently diagnosed based on areal bone mineral density (aBMD) computed from 2D DXA scans. However, aBMD is a limited surrogate for femoral strength since it does not account for 3D bone geometry and density distribution. QCT scans combined with finite element (FE) analysis can deliver improved femoral strength predictions. However, non-negligible radiation dose and high costs prevent a systematic usage of this technique for screening purposes. As an alternative, the 3D-Shaper software (3D-Shaper Medical, Spain) reconstructs the 3D shape and density distribution of the femur from 2D DXA scans. This approach could deliver a more accurate estimation of femoral strength than aBMD by using FE analysis on the reconstructed 3D DXA. Methods: Here we present the first independent evaluation of the software, using a dataset of 77 ex vivo femora. We extend a prior evaluation by including the density distribution differences, the spatial correlation of density values and an FE analysis. Yet, cortical thickness is left out of this evaluation, since the cortex is not resolved in our FE models. Results: We found an average surface distance of 1.16mm between 3D DXA and QCT images, which shows a good reconstruction of the bone geometry. Although BMD values obtained from 3D DXA and QCT correlated well (r 2 = 0.92), the 3D DXA BMD were systematically lower. The average BMD difference amounted to 64mg/cm3, more than one-third of the 3D DXA BMD. Furthermore, the low correlation (r 2 = 0.48) between density values of both images indicates a limited reconstruction of the 3D density distribution. FE results were in good agreement between QCT and 3D DXA images, with a high coefficient of determination (r 2 = 0.88). However, this correlation was not statistically different from a direct prediction by aBMD. Moreover, we found differences in the fracture patterns between the two image types. QCT-based FE analysis resulted mostly in femoral neck fractures and 3D DXA-based FE in subcapital or pertrochanteric fractures. Discussion: In conclusion, 3D-Shaper generates an altered BMD distribution compared to QCT but, after careful density calibration, shows an interesting potential for deriving a standardized femoral strength from a DXA scan.

Stomach Geometry Reconstruction Using Serosal Transmitting Coils and Magnetic Source Localization.

Bioelectric slow waves (SWs) are a key regulator of gastrointestinal motility, and disordered SW activity has been linked to motility disorders. There is currently a lack of practical options for the acquisition of the 3D stomach geometry during research studies when medical imaging is challenging. Accurately recording the geometry of the stomach and co-registering electrode and sensor positions would provide context for in-vivo studies and aid the development of non-invasive methods of gastric SW assessment. A stomach geometry reconstruction method based on the localization of transmitting coils placed on the gastric serosa was developed. The positions and orientations of the coils, which represented boundary points and surface-normal vectors, were estimated using a magnetic source localization algorithm. Coil localization results were then used to generate surface models. The reconstruction method was evaluated against four 3D-printed anatomically realistic human stomach models and applied in a proof of concept in-vivo pig study. Over ten repeated reconstructions, average Hausdorff distance and average surface-normal vector error values were 4.7 ±0.2 mm and 18.7 ±0.7° for the whole stomach, and 3.6 ±0.2 mm and 14.6 ±0.6° for the corpus. Furthermore, mean intra-array localization error was 1.4 ±1.1 mm for the benchtop experiment and 1.7 ±1.6 mm in-vivo. Results demonstrated that the proposed reconstruction method is accurate and feasible. The stomach models generated by this method, when co-registered with electrode and sensor positions, could enable the investigation and validation of novel inverse analysis techniques.

Feature-assisted interactive geometry reconstruction in 3D point clouds using incremental region growing

Reconstructing geometric shapes from point clouds is a common task that is often accomplished by experts manually modeling geometries in CAD-capable software. State-of-the-art workflows based on fully automatic geometry extraction are limited by point cloud density and memory constraints, and require pre- and post-processing by the user. In this work, we present a framework for interactive, user-driven, feature-assisted geometry reconstruction from arbitrarily sized point clouds. Based on seeded region-growing point cloud segmentation, the user interactively extracts planar pieces of geometry and utilizes contextual suggestions to point out plane surfaces, normal and tangential directions, and edges and corners. We implement a set of feature-assisted tools for high-precision modeling tasks in architecture and urban surveying scenarios, enabling instant-feedback interactive point cloud manipulation on large-scale data collected from real-world building interiors and facades. We evaluate our results through systematic measurement of the reconstruction accuracy, and interviews with domain experts who deploy our framework in a commercial setting and give both structured and subjective feedback.

Stretchable e-skin and transformer enable high-resolution morphological reconstruction for soft robots

Many robotic tasks require knowledge of the exact 3D robot geometry. However, this remains extremely challenging in soft robotics because of the infinite degrees of freedom of soft bodies deriving from their continuum characteristics. Previous studies have achieved only low proprioceptive geometry resolution (PGR), thus suffering from loss of geometric details (for example, local deformation and surface information) and limited applicability. Here we report an intelligent stretchable capacitive e-skin to endow soft robots with high PGR (3,900) bodily awareness. We demonstrate that the proposed e-skin can finely capture a wide range of complex 3D deformations across the entire soft body through multi-position capacitance measurements. The e-skin signals can be directly translated to high-density point clouds portraying the complete geometry via a deep architecture based on transformer. This high PGR proprioception system providing millimetre-scale, local and global geometry reconstruction (2.322 ± 0.687 mm error on a 20 × 20 × 200 mm soft manipulator) can assist in solving fundamental problems in soft robotics, such as precise closed-loop control and digital twin modelling. Developing proprioception systems for flexible structures such as soft robots is a challenge. Hu et al. report a stretchable e-skin for soft robot proprioception. Combined with deep learning, the e-skin enables high-resolution 3D geometry reconstruction of the soft robot and can be applied in many scenarios, such as human–robot interaction.

H-BIM and Artificial Intelligence: Classification of Architectural Heritage for Semi-Automatic Scan-to-BIM Reconstruction

We propose a semi-automatic Scan-to-BIM reconstruction approach, making the most of Artificial Intelligence (AI) techniques, for the classification of digital architectural heritage data. Nowadays, Heritage- or Historic-Building Information Modeling (H-BIM) reconstruction from laser scanning or photogrammetric surveys is a manual, time-consuming, overly subjective process, but the emergence of AI techniques, applied to the realm of existing architectural heritage, is offering new ways to interpret, process and elaborate raw digital surveying data, as point clouds. The proposed methodological approach for higher-level automation in Scan-to-BIM reconstruction is threaded as follows: (i) semantic segmentation via Random Forest and import of annotated data in 3D modeling environment, broken down class by class; (ii) reconstruction of template geometries of classes of architectural elements; (iii) propagation of template reconstructed geometries to all elements belonging to a typological class. Visual Programming Languages (VPLs) and reference to architectural treatises are leveraged for the Scan-to-BIM reconstruction. The approach is tested on several significant heritage sites in the Tuscan territory, including charterhouses and museums. The results suggest the replicability of the approach to other case studies, built in different periods, with different construction techniques or under different states of conservation.

Glacial geomorphology and Pleistocene glacier reconstruction in the Demänovská Valley, Low Tatra Mountains, Slovakia

In the Western Carpathians, clear evidence of the Pleistocene glaciations only occurs in two mountain massifs – the Tatra and Low Tatra Mountains. The Low Tatra Mountains (2043 m a.s.l.), contrary to the higher and more strongly glaciated Tatra Mountains (2654 m a.s.l.), have previously been much less attractive for scientific research. Hence, in these mountains, both glacial landforms and chronology, together with a detailed reconstruction of glacier geometry and resulted equilibrium line altitude (ELA), are poorly documented. The aim of this paper is to characterize the glacial relief and reconstruction of geometry and ELA of the Zadná voda glacier in the Demänovská Valley system which belongs to the category of the largest Pleistocene glaciers on the northern slope of the Low Tatra Mountains. The mapping results show that a freshly shaped, massive terminal moraine of maximal ice extent (MIE, likely formed during the global Last Glacial Maximum – LGM) occurs 4.3 km distance down-valley from the glacial cirque backwalls. There is no evidence of deposits from older glaciations beyond the terminal moraine down the valley. The terminal zone of the MIE features a fresh morainic landscape with hummocky topography with kettle hollows and the only known morainic lake in the Low Tatra Mountains – Vrbické pleso. During the MIE, the Zadná voda glacier covered 7 km2 of the area and featured a mean thickness of 48 m. The ELA of this glacier was 1433 m, determined by the area-altitude balance ratio (AABR) 1.6 method, which is a similar value to the LGM ELA calculated in the Western Tatra Mountains. The recessional stages were only recognized in the cirques area, where one or two generations of debris-covered glaciers and rock glaciers mark the final deglaciation of the study area.

Piuro Landslide: 3D Hydromechanical Numerical Modelling of the 1618 Event

The Piuro 1618 landslide represents a well-known case history of a large Alpine landslide. It destroyed the ancient village of Piuro (Italian Bregaglia Valley), renowned as an important trading center between the Mediterranean region and Northern Europe. The event had a significant impact among communities of all Alpine regions and was well documented by chronicles and paintings during subsequent decades. However, some aspects, such as the geometry reconstruction of the landslide body, the location of the landslide scarp, and its dynamics, remained undefined in previous studies, and a geomechanical characterization of the failure area is completely missing. Using field and laboratory analysis followed by stress–strain numerical modelling, this work develops a 3D conceptual geomechanical model of the slope considering its complex geological framework. The aim is to back-analyze the 1618 event, defining predisposing and triggering factors of the sliding event, and providing verifications on the geometry and location of the failure scar, as well as on the landslide dynamics. A coupled hydro-mechanical analysis with a 3D numerical approach is presented, assuming a rainfall scenario as a possible triggering factor. Simulated displacement and the development of a deep region of shear strain localization at a depth roughly corresponding to that of the detected Piuro sliding surface, allow us to highlight the mechanical role of geological elements outcropping along the slope and to validate the proposed scenario as a likely triggering factor for the 1618 event.

3D Multi-Modality Medical Imaging: Combining Anatomical and Infrared Thermal Images for 3D Reconstruction.

Medical thermography provides an overview of the human body with two-dimensional (2D) information that assists the identification of temperature changes, based on the analysis of surface distribution. However, this approach lacks spatial depth information, which can be enhanced by adding multiple images or three-dimensional (3D) systems. Therefore, the methodology applied for this paper generates a 3D point cloud (from thermal infrared images), a 3D geometry model (from CT images), and the segmented inner anatomical structures. Thus, the following computational processing was employed: Structure from Motion (SfM), image registration, and alignment (affine transformation) between the 3D models obtained to combine and unify them. This paper presents the 3D reconstruction and visualization of the respective geometry of the neck/bust and inner anatomical structures (thyroid, trachea, veins, and arteries). Additionally, it shows the whole 3D thermal geometry in different anatomical sections (i.e., coronal, sagittal, and axial), allowing it to be further examined by a medical team, improving pathological assessments. The generation of 3D thermal anatomy models allows for a combined visualization, i.e., functional and anatomical images of the neck region, achieving encouraging results. These 3D models bring correlation of the inner and outer regions, which could improve biomedical applications and future diagnosis with such a methodology.

Flow characteristics of positive and negative pressure irrigation in an immature tooth - A computational fluid dynamics study.

This study aims to investigate the irrigation dynamics in an immature tooth during positive and negative pressure irrigation using a computational fluid dynamics (CFDs) model. Cone-beam computed tomography scan of the maxillary central incisor with Cvek's stage III root development was used for the reconstruction of the root canal geometry. The computer-aided design models of open (front vent and notched) and closed (side vent [SV]) needles were positioned inside the root canal at two penetration depths, i.e., 3 mm and 1 mm short of apex. The negative pressure microcannula (MiC) was positioned at the level of the root apex. A prevalidated CFD model was used to simulate endodontic irrigation. The irrigant velocity in the apical root canal beyond the needle tip exceeded 0.1 m/s. As the needles were positioned closer to the apex, the wall shear stress (WSS) increased for the open-ended needles and decreased for the SV needle. MiC produced the lowest WSS. The mean apical pressure produced by the SV needle and MiC were below the critical threshold for periapical extrusion. The SV needle inserted within 1-3 mm of root apex during endodontic irrigation in an immature tooth allows adequate irrigant exchange with minimal risk of periapical extrusion.

Computational Geometry Reconstruction from 3D Topology Optimization Results: A New Parametric Approach by the Medial Axis

Computer-Aided Design and Applications is an international journal on the applications of CAD and CAM. It publishes papers in the general domain of CAD plus in emerging fields like bio-CAD, nano-CAD, soft-CAD, garment-CAD, PLM, PDM, CAD data mining, CAD and the internet, CAD education, genetic algorithms and CAD engines. The journal is aimed at all developers and users of CAD technology to ptovide CAD solutions for various stages of design and manufacturing. The journal publishes all about Computer-Aided Design and Computer-Aided technologies.