Search

Estimating 3D hand shape from a single-view RGB image is important for many applications. However, the diversity of hand shapes and postures, depth ambiguity, and occlusion may result in pose errors and noisy hand meshes. Making full use of 2D cues such as 2D pose can effectively improve the quality of 3D human hand shape estimation. In this paper, we use 2D joint heatmaps to obtain spatial details for robust pose estimation. We also introduce a depth-independent 2D mesh to avoid depth ambiguity in mesh regression for efficient hand-image alignment. Our method has four cascaded stages: 2D cue extraction, pose feature encoding, initial reconstruction, and reconstruction refinement. Specifically, we first encode the image to determine semantic features during 2D cue extraction; this is also used to predict hand joints and for segmentation. Then, during the pose feature encoding stage, we use a hand joints encoder to learn spatial information from the joint heatmaps. Next, a coarse 3D hand mesh and 2D mesh are obtained in the initial reconstruction step; a mesh squeeze-and-excitation block is used to fuse different hand features to enhance perception of 3D hand structures. Finally, a global mesh refinement stage learns non-local relations between vertices of the hand mesh from the predicted 2D mesh, to predict an offset hand mesh to fine-tune the reconstruction results. Quantitative and qualitative results on the FreiHAND benchmark dataset demonstrate that our approach achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]

With the increasing usage of three-dimensional meshes in Computer-Aided Design (CAD), medical imaging, and entertainment fields like virtual reality, etc., the authentication problems and awareness of intellectual property protection have risen over the last decade. Numerous watermarking schemes have been suggested to protect ownership and prevent the threat of data piracy. This paper begins with the potential difficulties that arose when dealing with three-dimension entities in comparison to two-dimensional entities and also lists possible algorithms suggested hitherto and their comprehensive analysis. Attacks, also play a crucial role in deciding on a watermarking algorithm so an attack based analysis is also presented to analyze the resilience of watermarking algorithms under several attacks. In the end, some evaluation measures and potential solutions are brooded over to design robust and oblivious watermarking schemes in the future. [ABSTRACT FROM AUTHOR]

Estimating 3D hand shape from a single-view RGB image is important for many applications. However, the diversity of hand shapes and postures, depth ambiguity, and occlusion may result in pose errors and noisy hand meshes. Making full use of 2D cues such as 2D pose can effectively improve the quality of 3D human hand shape estimation. In this paper, we use 2D joint heatmaps to obtain spatial details for robust pose estimation. We also introduce a depth-independent 2D mesh to avoid depth ambiguity in mesh regression for efficient hand-image alignment. Our method has four cascaded stages: 2D cue extraction, pose feature encoding, initial reconstruction, and reconstruction refinement. Specifically, we first encode the image to determine semantic features during 2D cue extraction; this is also used to predict hand joints and for segmentation. Then, during the pose feature encoding stage, we use a hand joints encoder to learn spatial information from the joint heatmaps. Next, a coarse 3D hand mesh and 2D mesh are obtained in the initial reconstruction step; a mesh squeeze-and-excitation block is used to fuse different hand features to enhance perception of 3D hand structures. Finally, a global mesh refinement stage learns non-local relations between vertices of the hand mesh from the predicted 2D mesh, to predict an offset hand mesh to fine-tune the reconstruction results. Quantitative and qualitative results on the FreiHAND benchmark dataset demonstrate that our approach achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]

With the widespread availability and utilization of 3D meshes across various applications, the need for accurately assessing their visual quality has become increasingly important. Despite the significance of this task, the literature offers few No-Reference (NR) approaches for evaluating the visual quality of 3D meshes. In response to this gap, this paper proposes a novel NR approach tailored specifically to score the quality of 3D meshes. After rendering a 3D mesh into 2D views and patches, a pre-trained convolutional neural network automatically extracts deep features from. These features are then employed in a Multi-Layer Perceptron regressor to predict the quality score of the rendered images. The obtained scores are combined with their corresponding BRISQUE scores, and an additional MLP regressor is used to predict the final score. We present experimental results demonstrating the effectiveness and robustness of our approach across a diverse range of 3D mesh datasets. Comparative analyses with existing NR methods underscore the superior performance and versatility of the proposed approach. Overall, this paper contributes to the advancement of NR techniques for assessing 3D mesh quality, offering a valuable tool for researchers, practitioners, and developers working with 3D models across various domains.

The design and manufacturing strategy using reverse engineering (RE) for Miranda Kerr Tea for One Teapot are presented in this paper. A computer-aided reverse engineering system (CARE System) was applied to minimize file errors generated by scanning Miranda Kerr Tea for One Teapot sample products made from Bone China clay. Digital data from the scanning process is used to design a teapot model that is precise and accurate. The digital data generated by Next Engine 3D and the priXa 1588 CMM is then converted into stereolithography (STL) file format (triangle-based data). The process of making 3D CAD models consists of: editing the 3D mesh from the scanning results, 3D CAD design forming the size of the fire, the size of the model, and the 3D CAD milling process using PowerSHAPE with the final result in the form of the surface of each part of the Teapot product. Manufacturing optimization to get the optimal machining strategy used PowerMILL and CNC machines. The casting process becomes a follow-up process after machining the mold of the designed product. This research has succeeded in demonstrating the advantages of using CARE System technology in the national ceramic industry in Indonesia so that it can compete at national and international levels. This is based on the magnitude of the RE error value of less than 1.00 mm with a total processing time of 43 hours 18 minutes 10 seconds and a total cost of about $ 4172.35. [ABSTRACT FROM AUTHOR]

This paper proposes a fast method for measuring the partial Similarity between 3D Model and 3D point Cloud (SimMC). It is crucial to measure SimMC for many point cloud-related applications such as 3D object retrieval and inverse procedural modelling. In our proposed method, the surface area of model and the Distance from Model to point Cloud (DistMC) are exploited as measurements to calculate SimMC. Here, DistMC is defined as the weighted distance of the distances between points sampled from model and point cloud. Similarly, Distance from point Cloud to Model (DistCM) is defined as the average distance of the distances between points in point cloud and model. In order to reduce huge computational burdens brought by calculation of DistCM in some traditional methods, we define SimMC as the ratio of weighted surface area of model to DistMC. Compared to those traditional SimMC measuring methods that are only able to measure global similarity, our method is capable of measuring partial similarity by employing distance-weighted strategy. Moreover, our method is able to be faster than other partial similarity assessment methods. We demonstrate the superiority of our method both on synthetic data and laser scanning data. [ABSTRACT FROM AUTHOR]

Inspection and documentation of masonry structures is a time-consuming and expensive process that heavily relies on an engineer's expertise. This paper introduces a computer vision-based method that automates the creation of classified point clouds from 3D reconstruction models obtained through photogrammetry and/or laser scanning. By leveraging Convolutional Neural Networks (CNN) on 3D renders, the proposed methodology can be used to classify structural features (i.e., blocks, mortar, cracks) with greater accuracy and less effort than conventional methods. Moreover, this approach is flexible and can include further classifications by incorporating additional CNN models, allowing broader applications across various materials (i.e., concrete, steel, timber) and defects. Additionally, a precise methodology for accurate crack quantification featuring a manual annotation tool was introduced which was validated using outputs from a full-scale masonry arch bridge test carried out in the laboratory. The results emphasize the robustness of the classification approach and highlight the useful geometric information that can be gained from full-scale masonry structures. The proposed approach has the potential to use image data from UAVs/static cameras and revolutionize the way we document and inspect structures in the future. • Classification of 3D point-cloud of masonry fabric via semantic-segmentation on reality-mesh models. • Automatic detection of cracks from 3D reconstruction models of masonry structures • Quantification of the extend of detected cracks in 3D space. • Comparison of 3D photogrammetry software using a case study of an experimental masonry arch bridge. [ABSTRACT FROM AUTHOR]

Creating 3D building models in large scale is becoming more popular and finds many applications. Nowadays, a wide term “3D building models" can be applied to several types of products: well-known CityGML solid models (available on few Levels of Detail), which are mainly generated from Airborne Laser Scanning (ALS) data, as well as 3D mesh models that can be created from both nadir and oblique aerial images. City authorities and national mapping agencies are interested in obtaining the 3D building models. Apart from the completeness of the models, the accuracy aspect is also important. Final accuracy of a building model depends on various factors (accuracy of the source data, complexity of the roof shapes, etc.). In this paper the methodology of inspection of dataset containing 3D models is presented. The proposed approach check all building in dataset with comparison to ALS point clouds testing both: accuracy and level of details. Using analysis of statistical parameters for normal heights for reference point cloud and tested planes and segmentation of point cloud provides the tool that can indicate which building and which roof plane in do not fulfill requirement of model accuracy and detail correctness. Proposed method was tested on two datasets: solid and mesh model. [ABSTRACT FROM AUTHOR]

Abstract Estimating 3D hand shape from a single-view RGB image is important for many applications. However, the diversity of hand shapes and postures, depth ambiguity, and occlusion may result in pose errors and noisy hand meshes. Making full use of 2D cues such as 2D pose can effectively improve the quality of 3D human hand shape estimation. In this paper, we use 2D joint heatmaps to obtain spatial details for robust pose estimation. We also introduce a depth-independent 2D mesh to avoid depth ambiguity in mesh regression for efficient hand-image alignment. Our method has four cascaded stages: 2D cue extraction, pose feature encoding, initial reconstruction, and reconstruction refinement. Specifically, we first encode the image to determine semantic features during 2D cue extraction; this is also used to predict hand joints and for segmentation. Then, during the pose feature encoding stage, we use a hand joints encoder to learn spatial information from the joint heatmaps. Next, a coarse 3D hand mesh and 2D mesh are obtained in the initial reconstruction step; a mesh squeeze-and-excitation block is used to fuse different hand features to enhance perception of 3D hand structures. Finally, a global mesh refinement stage learns non-local relations between vertices of the hand mesh from the predicted 2D mesh, to predict an offset hand mesh to fine-tune the reconstruction results. Quantitative and qualitative results on the FreiHAND benchmark dataset demonstrate that our approach achieves state-of-the-art performance.

This paper presents a multivariate UPD estimator, family member [A,U,T] with parameters p and s, which allows to calculate simultaneously parameters of Weibull K and C at a point Pe from the measured values of these variables in several sampling points. During the 3D estimation, the spatial relationship between the data and the associated values of elevation and roughness of the terrain is taken into account; with the estimated results, a model of wind energy resources is developed, given by a 3D mesh where to each node is associated the values of K and C. Finally, a method of combinatory optimization is described to find the values of p and s such that the mesh model is feasible and optimal for the given data. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new approach to get the optimal segmentation of a 3D mesh as a human can perceive using the minima rule and spectral clustering. This method is fully unsupervised and provides a hierarchical segmentation via recursive cuts. We introduce a new concept of the adjacency matrix based on cognitive studies. We also introduce the use of one-spectral clustering which leads to the optimal Cheeger cut value. [ABSTRACT FROM PUBLISHER]

3D polygon mesh is an important and popular representation of 3D shapes in the field of computer graphics and computer-aided design. Recent works have introduced deep neural networks for mesh data analysis. However, it remains a great challenge for convolutional neural networks to learn mesh shape effectively due to the difficulty of deriving long-range information from the irregular data structure. Another tricky problem is how to explore a high effective representation of the input feature for mesh learning network. In this paper, we propose a novel 3D mesh learning method, named TPNet, which enhances the perception and learns long-range information by customizing dilated convolution for non-uniform mesh data. Specifically, we devise a faithful strategy that accurately locates the position where dilated convolutions can be adopted, despite the non-uniformity and irregularity of the mesh data. Furthermore, our method proposes a topology-preserved 7-dimension feature representation for mesh data and aggregates the features via stacks of convolution layers and dilated convolution layers. Extensive experiments demonstrate the effectiveness of our approach on 3D mesh learning tasks, where we show superior or at least comparable performance to the SOTA approaches. • This work is the first to extend dilated convolution to edges for non-uniform mesh data. • Dilated convolution on mesh edges enhances the perception without increasing computation costs. • We explore the characteristics of 3D mesh and propose a topology-preserved edge feature. • Our TPNet achieves superior or at least comparable performance to SOTA methods. [ABSTRACT FROM AUTHOR]

The high-precision generation of 3D building models is a controversial research topic in the field of smart cities. However, due to the limitations of single-source data, existing methods cannot simultaneously balance the local accuracy, overall integrity, and data scale of the building model. In this paper, we propose a novel 3D building model generation method based on multi-source 3D data fusion of 3D point cloud data and 3D mesh data with deep learning method. First, A Multi-Source 3D data Quality Evaluation Network (MS3DQE-Net) is proposed for evaluating the quality of 3D meshes and 3D point clouds. Then, the evaluation results are utilized to guide 3D building model generation. The MS3DQE-Net uses 3D meshes and 3D point clouds as inputs and fuses the learned features to obtain a more complete shape description. To train MS3DQE-Net, a multi-source 3D dataset is constructed, which collected from a real scene based on mobile laser scanning (MLS) 3D point clouds and 3D mesh data, including pairs of matching 3D meshes and 3D point clouds of the 3D building model. Specifically, to our knowledge, we are the first researchers to propose such multi-source 3D dataset. The experimental results show that MS3DQE-Net achieves a state-of-the-art performance in multi-source 3D data quality evaluation. We demonstrate the large-scale and high-precision, 3D building model generation approach on a campus.

As one of the main trends of communication technology for 3D integrated circuits, the 3D networks-on-chip (NoCs) have drawn high concern from the academia. The links are main components of the NoCs. For the permanent link faults, the fault-tolerant routing scheme has been regarded as an effective mechanism to ensure the performance of the 2D NoCs. In this paper, we propose a low-overhead fault-tolerant routing scheme called LOFT for 3D Mesh NoCs without requiring any virtual channels (VCs). LOFT is a deadlock-free scheme by adopting a logic-based routing named LBDRe 2 guided by a turn model Complete-OE. The experimental results show that LOFT possesses better performance, improved reliability and lower overhead compared with the state-of-the-art reliable routing schemes. [ABSTRACT FROM AUTHOR]

Deep learning and neural networks are being extended to geometric design and computation. Recent studies show that deep neural networks are vulnerable to adversarial samples. However, for 3D mesh adversarial samples, the most related studies actually attack the 2D victim networks, in which they have to project 3D objects to 2D images. In this paper, we present D3AdvM (Direct 3D adversary for mesh) to directly generate adversarial samples inside mesh data. Specifically, we propose two adversary generation approaches: vertex-based and edge-based. The first one, 3DVP (3D Vertex-based Perturbation), skillfully searches the optimized vertices positions based on opposite gradient fitness. The second one, KES (Key Edge-based Selection), carefully collapses the key feature edges according to importance of edge feature. Thus, our approaches avoid 3D/2D projections and approximation errors. Also, our approach can reduce the computation overhead. In addition, the proposed D3AdvM can control the number of perturbed vertices for real-world engineering designs and applications. Extensive experiments show that the generated 3D meshes are effective to attack classification networks. Furthermore, we evaluate the transferability, in which D3AdvM can attack both mesh-based networks and point cloud-based networks as victim networks. Our findings could benefit 3D geometry design based on the new generation of artificial intelligence and big data. • This work is the first one to directly attack mesh-based neural networks with adversarial meshes in 3D space without the 2D projection. • We explore the characteristics of 3D mesh topological entities and propose both vertex-based and edge-based adversarial approaches. • D3AdvM can constrain the adversarial samples within a specific number to support high feasibility in real-world applications. • D3AdvM shows valuable transferability to attack different versions of mesh-based networks and even the point cloud-based networks. • Our findings could benefit 3D geometry design based on the new generation of artificial intelligence and big data. [ABSTRACT FROM AUTHOR]

The visual equivalent of human face exhibiting articulatory expression of a unit of sound in spoken language is termed as Viseme. The Visemes can be used to teach hearing impaired students visually and effectively. In this paper a method to construct three dimensional human faces from a single 2D image is proposed. By this method a generic 3D mesh of human face is deformed using the calculated feature points from 2D images. The method consists of the following steps namely locate corresponding feature vertices in both 2D image and the generic 3D mesh, calculating the corresponding 3D co-ordinates of the 2D feature points and relative camera position and finally deforming the generic 3D mesh using the Radial Basis Function (RBF) based interpolation. Later the constructed three dimensional models can be animated by morphing different visemes together. The inner articulatory organs are modelled using Java3D and blended with these constructed 3D dimensional units. [ABSTRACT FROM AUTHOR]

Contemporary advances in technology have allowed the transfer of knowledge from industrial laser melting systems to surgery; such an approach could increase the degree of accuracy in orbital restoration. The aim of this study was to examine the accuracy of selective laser melted PSIs (patient-specific implants) and navigation in primary orbital reconstruction. Ninety-six patients with orbital fractures were included in this study. Planned vs. achieved orbital volumes (a) and angles (b) were compared to the unaffected side (n = 96). The analysis included the overlay of post-treatment on planned images (iPlan 3.0.5, Brainlab®, Feldkirchen, Germany). The mean difference in orbital volume between the digitally planned orbit and the postoperative orbit was 29.16 cm3 (SD 3.54, presurgical) to 28.33 cm3 (SD 3.64, postsurgical, t = 5.00, df = 95.00; p < 0.001), resulting in a mean volume difference (planned vs. postop) of less than 1 cm3. A 3D analysis of the color mapping showed minor deviations compared to the mirrored unaffected side. The results suggested that primary reconstruction in complex orbital wall fractures can be routinely achieved with a high degree of accuracy by using selective laser melted orbital PSIs. [ABSTRACT FROM AUTHOR]

We propose a preprocessing system that transforms the real world into 3D mesh virtual world to provide augmented reality (AR) services. The proposed system uses a monocular RGB camera to obtain sequential images to generate real space. First, we create 3D real-world space composed of point clouds using sequential color images. And then, we segment the objects in each color image and assign an identification number for each object. Also, we execute ‘3D point labeling’, which assigns identification numbers from 2D segmented object to 3D point cloud through a simple projection manner with several parameters. This process could collect 3D point cloud with same the label by as an object. Finally, only the 3D point clouds that have the same identification number by as an object are used to generate 3D mesh. This paper confirmed that 3D mesh could be created using the only general monocular camera without the help of special 3D sensors.

Facial caricature is the art of drawing faces in an exaggerated way to convey emotions such as humor or sarcasm. Automatic caricaturization has been explored both in the 2D and 3D domain. In this paper, we propose two novel approaches to automatically caricaturize input facial scans, filling gaps in the literature in terms of user-control, caricature style transfer, and exploring the use of deep learning for 3D mesh caricaturization. The first approach is a gradient-based differential deformation approach with data driven stylization. It is a combination of two deformation processes: facial curvature and proportions exaggeration. The second approach is a GAN for unpaired face-scan-to-3D-caricature translation. We leverage existing facial and caricature datasets, along with recent domain-to-domain translation methods and 3D convolutional operators, to learn to caricaturize 3D facial scans in an unsupervised way. To evaluate and compare these two novel approaches with the state of the art, we conducted the first user study of facial mesh caricaturization techniques, with 49 participants. It highlights the subjectivity of the caricature perception and the complementarity of the methods. Finally, we provide insights for automatically generating caricaturized 3D facial mesh.

Abstract: In order to locate the corner vertices on 3D mesh precisely, the paper proposes a novel method by extend the SUSAN operator to the 3D data. The algorithm selected the candidate corners by multi-stage adjacent information, calculated the deformation value on each candidate point, determined the 3D corners by deformation and finally applied nonmaximum suppression within the specified range for removing false point. Experiment results in real 3D models show the algorithm''s validity and superiority [Copyright &y& Elsevier]

Abstract: In order to detect the feature edges on 3D mesh precisely, the paper proposes a novel algorithm by extend the Canny detector to the 3D data. The algorithm first selected the candidate feature vertexes by multi-stage adjacent information, calculated the deformation value on each candidate point; Then, calculated the edge''s sharpness value by endpoint''s deformation value and other related information, calculated the statistical data on sharpness value to determine two threshold value; Finally, filtered out the seminal edges by higher threshold value, applied nonmaximum suppression within the specified range for removing false feature edges, extended the seminal edge by lower value to get complete edge. Experiment results in real 3D models show the algorithm''s validity and superiority [Copyright &y& Elsevier]

Abstract: In order to detect the feature edges on 3D mesh precisely, the paper proposes an effective algorithm by using the related endpoint''s information to detect the 3D edge. The algorithm first selected the candidate feature vertexes by multi-stage adjacent information, calculated the deformation value on each candidate point; Then calculated the edge''s feature value by endpoint''s deformation value and other related information, calculated the statistical data on feature value to determine two threshold value; Finally, filtered out the seminal feature edges by higher threshold value, extended the feature edges by lower value to get complete edge, filtered the false feature edges by total length and linearity. Experiment results in real 3D models show the algorithm''s validity and superiority [Copyright &y& Elsevier]

Abstract: This paper presents a robust and blind watermarking algorithm for three-dimensional (3D) meshes. The watermarking primitive is an intrinsic 3D shape descriptor: the analytic and continuous geometric volume moment. During watermark embedding, the input mesh is first normalized to a canonical and robust spatial pose by using its global volume moments. Then, the normalized mesh is decomposed into patches and the watermark is embedded through a modified scalar Costa quantization of the zero-order volume moments of some selected candidate patches. Experimental results and comparisons with the state of the art demonstrate the effectiveness of the proposed approach. [Copyright &y& Elsevier]

The design and manufacturing strategy using reverse engineering (RE) for Miranda Kerr Tea for One Teapot are presented in this paper. A computer-aided reverse engineering system (CARE System) was applied to minimize file errors generated by scanning Miranda Kerr Tea for One Teapot sample products made from Bone China clay. Digital data from the scanning process is used to design a teapot model that is precise and accurate. The digital data generated by Next Engine 3D and the priXa 1588 CMM is then converted into stereolithography (STL) file format (triangle-based data). The process of making 3D CAD models consists of: editing the 3D mesh from the scanning results, 3D CAD design forming the size of the fire, the size of the model, and the 3D CAD milling process using PowerSHAPE with the final result in the form of the surface of each part of the Teapot product. Manufacturing optimization to get the optimal machining strategy used PowerMILL and CNC machines. The casting process becomes a follow-up process after machining the mold of the designed product. This research has succeeded in demonstrating the advantages of using CARE System technology in the national ceramic industry in Indonesia so that it can compete at national and international levels. This is based on the magnitude of the RE error value of less than 1.00 mm with a total processing time of 43 hours 18 minutes 10 seconds and a total cost of about $ 4172.35.

Copyright of Revista Facultad de Ingeniería - UPTC is the property of Universidad Pedagogica y Tecnologica de Colombia, Facultad de Ingenieria and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)