Search

3D reconstruction from single-view images is a long-standing research problem. To date, there are various methods based on point clouds and volumetric representations. In spite of success in 3D models generation, it is quite challenge for these approaches to deal with models with complex topology and fine geometric details. Thanks to the recent advance of deep shape representations,learning the structure and detail representation using deep neural networks is a promising direction. In this paper, we propose a novel approach named STD-Net to reconstruct 3D models utilizing mesh representation that is well suited for characterizing complex structures and geometry details. Our method consists of (1) an auto-encoder network for recovering the structure of an object with bounding box representation from a single-view image; (2) a topology-adaptive GCN for updating vertex position for meshes of complex topology; and (3) a unified mesh deformation block that deforms the structural boxes into structure-aware meshes. Evaluation on ShapeNet shows that STD-Net has better performance than state-of-the-art methods in reconstructing complex structures and fine geometric details.

The topology of isosurfaces changes at isovalues of critical points, making such points an important feature when building contour trees or Morse-Smale complexes. Hexahedral elements with linear interpolants can contain additional off-vertex critical points in element bodies and on element faces. Moreover, a point on the face of a hexahedron which is critical in the element-local context is not necessarily critical in the global context. In ‘`Exploring Scalar Fields Using Critical Isovalues’' Weber et al. introduce a method to determine whether critical points on faces are also critical in the global context, based on the gradient of the asymptotic decider in each element that shares the face. However, as defined, the method of Weber et al. contains an error, and can lead to incorrect results. In this work we correct the error.

Mesh denoising is a critical technology in geometry processing that aims to recover high-fidelity 3D mesh models of objects from noise-corrupted versions. In this work, we propose a learning-based mesh normal denoising scheme, called NormalNet, which employs deep networks to find the correlation between the volumetric representation and denoised face normal. Overall, NormalNet follows the iterative framework of filtering-based mesh denoising. During each iteration, firstly, a local partition normalization strategy is applied to split the local structure around each face into dense voxels, in which both the structure and face normal information can be preserved during this transformation. Benefiting from the thorough information preservation, we can use simple residual networks, which employ the volumetric representation as the input and produce the learned denoised face normal, to achieve satisfactory results. Finally, the vertex positions are updated according to the denoised normals. Besides introducing normalization into mesh denoising, our main contributions include a classification-based training faces selection strategy for balancing the training set and a mismatched-faces rejection strategy for removing the mismatched faces between noisy mesh and ground truth. Compared to state-of-the-art works, NormalNet can effectively remove noise while preserving the original features and avoiding pseudo-features.

We introduce Neural Marching Cubes (NMC), a data-driven approach for extracting a triangle mesh from a discretized implicit field. Classical MC is defined by coarse tessellation templates isolated to individual cubes. While more refined tessellations have been proposed, they all make heuristic assumptions, such as trilinearity, when determining the vertex positions and local mesh topologies in each cube. In principle, none of these approaches can reconstruct geometric features that reveal coherence or dependencies between nearby cubes (e.g., a sharp edge), as such information is unaccounted for, resulting in poor estimates of the true underlying implicit field. To tackle these challenges, we re-cast MC from a deep learning perspective, by designing tessellation templates more apt at preserving geometric features, and learning the vertex positions and mesh topologies from training meshes, to account for contextual information from nearby cubes. We develop a compact per-cube parameterization to represent the output triangle mesh, while being compatible with neural processing, so that a simple 3D convolutional network can be employed for the training. We show that all topological cases in each cube that are applicable to our design can be easily derived using our representation, and the resulting tessellations can also be obtained naturally and efficiently by following a few design guidelines. In addition, our network learns local features with limited receptive fields, hence it generalizes well to new shapes and new datasets. We evaluate our neural MC approach by quantitative and qualitative comparisons to all well-known MC variants. In particular, we demonstrate the ability of our network to recover sharp features such as edges and corners, a long-standing issue of MC and its variants. Our network also reconstructs local mesh topologies more accurately than previous approaches., Comment: Accepted to SIGGRAPH Asia 2021. Code: https://github.com/czq142857/NMC, supplementary material: https://www.sfu.ca/~zhiqinc/nmc/NMC_supplementary.zip

To maintain pipeline transportation’s optimal efficiency and safety, pipelines must be regularly inspected and cleaned by the pipeline inspection gauge (PIG). Since the PIG passes through the whole pipeline, which is generally tens of kilometers, observing where the PIG is working in real-time is necessary. When the PIG passes through the pipe joint, the vibration signal will generate by the collision between the PIG and the girth weld, which can transmit along the fiber cable besides the pipeline. In this paper, we demonstrate that the optical fiber distributed acoustic sensing (DAS) can acquire the collision vibration in terms of the V pattern in the waterfall diagram, whose vertex is the collision position of PIG. The vertex will not exist when the cable positions are far away from the pipeline, which is relatively common in practice. We proposed an algorithm based on the clustering algorithm and the Hough transform to detect the position of the PIG even when the vertex of the V pattern does not exist. A field experiment shows that the proposed positioning algorithms applied to the DAS can effectively track the PIG online.

Graphics processing units (GPUs) power today’s fastest supercomputers, are the dominant platform for deep learning, and provide the intelligence for devices ranging from self-driving cars to robots and smart cameras. They also generate compelling photorealistic images at real-time frame rates. GPUs have evolved by adding features to support new use cases. NVIDIA’s GeForce 256, the first GPU, was a dedicated processor for real-time graphics, an application that demands large amounts of floating-point arithmetic for vertex and fragment shading computations and high memory bandwidth. As real-time graphics advanced, GPUs became programmable. The combination of programmability and floating-point performance made GPUs attractive for running scientific applications. Scientists found ways to use early programmable GPUs by casting their calculations as vertex and fragment shaders. GPUs evolved to meet the needs of scientific users by adding hardware for simpler programming, double-precision floating-point arithmetic, and resilience.

At present, multi-oriented text detection methods based on deep neural network have achieved promising performances on various benchmarks. Nevertheless, there are still some difficulties for arbitrary shape text detection, especially for a simple and proper representation of arbitrary shape text instances. In this paper, a pixel-based text detector is proposed to facilitate the representation and prediction of text instances with arbitrary shapes in a simple manner. Firstly, to alleviate the influence of the target vertex sorting and achieve the direct regression of arbitrary shape text instances, the starting-point-independent coordinates regression loss is proposed. Furthermore, to predict more accurate text instances, the text instance accuracy loss is proposed as an assistant task to refine the predicted coordinates under the guidance of IoU. To evaluate the effectiveness of our detector, extensive experiments have been carried on public benchmarks which contain arbitrary shape text instances and multi-oriented text instances. We obtain 84.8% of F-measure on Total-Text benchmark. The results show that our method can reach state-of-the-art performance.

Inspired by the ability of water to assimilate any shape, if being poured into it, regardless if flat, round, sharp, or pointy, we present a novel, high-quality meshing method. Our algorithm creates a triangulated mesh, which automatically refines where necessary and accurately aligns to any target, given as mesh, point cloud, or volumetric function. Our core optimization iterates over steps for mesh uniformity, point cloud projection, and mesh topology corrections, always guaranteeing mesh integrity and $$\epsilon $$ ϵ -close surface reconstructions. In contrast with similar approaches, our simple algorithm operates on an individual vertex basis. This allows for automated and seamless transitions between the optimization phases for rough shape approximation and fine detail reconstruction. Therefore, our proposed algorithm equals established techniques in terms of accuracy and robustness but supersedes them in terms of simplicity and better feature reconstruction, all controlled by a single parameter, the intended edge length. Due to the overall increased versatility of input scenarios and robustness of the assimilation, our technique furthermore generalizes multiple established approaches such as ballooning or shrink wrapping.

While commodity GPUs provide a continuously growing range of features and sophisticated methods for accelerating compute jobs, many state-of-the-art solutions for point cloud rendering still rely on the provided point primitives (GL_POINTS, POINTLIST, ...) of graphics APIs for image synthesis. In this paper, we present several compute-based point cloud rendering approaches that outperform the hardware pipeline by up to an order of magnitude and achieve significantly better frame times than previous compute-based methods. Beyond basic closest-point rendering, we also introduce a fast, high-quality variant to reduce aliasing. We present and evaluate several variants of our proposed methods with different flavors of optimization, in order to ensure their applicability and achieve optimal performance on a range of platforms and architectures with varying support for novel GPU hardware features. During our experiments, the observed peak performance was reached rendering 796 million points (12.7GB) at rates of 62 to 64 frames per second (50 billion points per second, 802GB/s) on an RTX 3090 without the use of level-of-detail structures. We further introduce an optimized vertex order for point clouds to boost the efficiency of GL_POINTS by a factor of 5x in cases where hardware rendering is compulsory. We compare different orderings and show that Morton sorted buffers are faster for some viewpoints, while shuffled vertex buffers are faster in others. In contrast, combining both approaches by first sorting according to Morton-code and shuffling the resulting sequence in batches of 128 points leads to a vertex buffer layout with high rendering performance and low sensitivity to viewpoint changes., Comment: 13 pages content, 5 pages appendix

Mesh models generated by multi view stereo (MVS) algorithms often fail to represent in an adequate manner the sharp, natural edge details of the scene. The harsh depth discontinuities of edge regions are eventually a challenging task for dense reconstruction, while vertex displacement during mesh refinement frequently leads to smoothed edges that do not coincide with the fine details of the scene. Meanwhile, 3D edges have been used for scene representation, particularly man-made built environments, which are dominated by regular planar and linear structures. Indeed, 3D edge detection and matching are commonly exploited either to constrain camera pose estimation, or to generate an abstract representation of the most salient parts of the scene, and even to support mesh reconstruction. In this work, we attempt to jointly use 3D edge extraction and MVS mesh generation to promote edge detail preservation in the final result. Salient 3D edges of the scene are reconstructed with state-of-the-art algorithms and integrated in the dense point cloud to be further used in order to support the mesh triangulation step. Experimental results on benchmark dataset sequences using metric and appearance-based measures are performed in order to evaluate our hypothesis.

This paper presents a method to avoid collisions and deadlocks between mobile robots working collaboratively in a shared physical environment. Based on the shared knowledge of the robot’s direction and coordinates, we define five conflict types between robots and propose a new concept named Artificial Untraversable Vertex (AUV) to resolve the potential conflicts. Since conflict avoidance between robots is typically a real-time process, a heuristic search algorithm D* Lite with fast replanning characteristics is introduced. Once a robot finds that it may collide with another robot while moving along the preplanned path, a new conflict-free path can be calculated based on the AUV and D* Lite. The experimental results demonstrate that the proposed Multi-Robot Path Planning (MRPP) method can effectively avoid collisions and deadlocks between mobile robots.

In this paper, a calibration method based on a two-step extended Kalman filter (EKF) is proposed. Firstly, the four vertex positions of a rectangle in the environment are calibrated. Specifically, in the first stage the initial position states of all anchor nodes are obtained using a rough localization method. In the second stage, the first and second step EKFs are used to obtain the real-time state of the measured target and all anchor nodes. The state estimation of all anchor nodes is achieved by employing the iterative process of the two-step EKF. The effectiveness and stability of the proposed algorithm are verified by simulations and experiment.

Direct triangular surface remeshing algorithms work directly on the surface meshes without involving any complex parameterization techniques. The typical goal of surface remeshing is to find a mesh that is a faithful approximation of the input mesh that maintains the geometric fidelity between input and output meshes, achieve a lower bound on the minimal angles to enhance high element quality while maintaining vertex regularity and sharp feature preservation of the input mesh. The goal of each surface remeshing algorithm varies as per the requirement of the end application and thus achieving a balance between all common goals is a challenging task in remeshing. In this paper, a survey of numerous direct surface remeshing algorithms that have been developed over the past decade is presented. A framework of direct surface remeshing is defined and various phases of the framework are discussed in detail to give new insights into both existing methods and issues. A detailed analysis of how significant challenges have already been overcome and promising perspectives of various methods are presented.

In recent past 2D metal trihalides have evolved as useful gapless semiconductor due to their physical properties like low dimensional magnetism and thermo electric performance. Such highly appreciable physical properties of these material are because enormous natural properties like half-metallicity, polarization, spin-orbit coupling impacts, layered structure and low cost. Layered formation of these materials provides an opportunity for the field of mathematical chemistry for identification of patterns and computation of mathematical properties. This article is dedicated to compute vertex-edge-degree based topological characterization of 2D trihalides. General mathematical expressions of several vertex-edge-degree based topological indices are presented in terms of research outcomes so they can be effectively used in future industrial projects.

Currently, mainstream 3D steganographic algorithms embed data through geometric modifications. To enhance the anti-steganalysis ability of such algorithms, we propose an additive Gaussian noise model for 3D mesh steganography. Our work starts with a theoretical analysis for correlations of vertex coordinate components. Based on this analysis, the whole embedding operation is decomposed into three independent tasks that target three vertex coordinate components, respectively. To obtain vertex-changing probabilities, we construct a payload-limited sender (PLS) problem aimed at minimizing the Kullback-Leibler divergence between the cover and stego mesh distributions for a given payload. Next, vertex coordinates are quantified so that the PLS problem can be solved in practice. Finally, a ternary embedding scheme is taken as a typical steganographic case. Although the proposed Gaussian model is simple and idealized, the experimental results demonstrate that our algorithm possesses the adaptivity and can achieve better anti-steganalysis performance at low payloads than most modern high-capacity 3D mesh steganography based on the geometric modification.

We propose a novel deep learning method to predict dense correspondences for partial point clouds of non-rigidly deformable targets. Dense correspondences are learned in the form of vertex displacements of a template mesh towards the point clouds. A two-stage regression framework is proposed to estimate accurate displacement vectors, including the global and local regression networks. Specifically, the global regression network estimates global displacements from the global features of the template mesh and point clouds through a graph CNN based hierarchical encoder-decoder network. Based on the initial displacements, a mesh can be generated that fits to the point clouds roughly. In the local regression network, a local feature embedding layer fuses local features of point clouds with graph features on the generated mesh through an attention mechanism. Consequently, the embedded local features are employed to refine the correspondences in local regions of the targets by predicting the increments of vertex displacements. Our method is further generalized to correspondence estimation on unseen real data with a robust fine-tuning method. The experimental results on diverse datasets of various deformable subjects (e.g., human bodies, animals, and hands) demonstrate that the proposed approach can accurately and robustly estimate dense correspondences from non-rigid point clouds.

To achieve high tampering localization precision and low distortion, a semi-fragile reversible watermarking for authenticating 2D engineering graphics is proposed based on an improved region nesting and a novel watermark generation. First, an intensive investigation is performed to the recently proposed region nesting (RN) partition. It is found that the original vertex and its mapped one cannot be guaranteed to be on the same line, which means that it still has room for improvement in term of distortion. Based on this, an improved region nesting partition (IRN) is proposed. Secondly, inspiring by the idea of soldiers parading, a novel watermark generation based on the short hash of the adjacent geometric features is developed. Then, a new coordinate system is constructed to achieve invariability of translation, scaling, rotation and entity re-arrangement. Based on the above techniques, a semi-fragile reversible watermarking for authenticating 2D engineering graphics is put forward. Experimental results and analysis show that IRN can obtain at least 15% distortion reduction compared with RN, the precision of tampering localization can be improved to a single vertex, and a certain semi-fragility in translation, scaling, rotation, and entity re-arrangement can be achieved. Furthermore, it has no file size expansion, and can obtain a good balance among imperceptibility, semi-fragility and tampering localization precision.

Cloth dynamics and collision handling are the two most challenging topics in cloth simulation. While researchers have substantially improved the performances of cloth dynamics solvers recently, their success in fast collision detection and handling is rather limited. In this article, we focus our research on the safety, efficiency, and realism of the repulsion-based collision handling approach, which has demonstrated its potential in existing GPU-based simulators. Our first discovery is the necessary vertex distance conditions for cloth to enter self intersections, the negations of which can be viewed as vertex distance constraints continuous in time for sufficiently avoiding self collisions. Continuous constraints, however, cannot be enforced with ease. Our solution is to convert continuous constraints into three types of constraints: discrete edge length constraints, discrete vertex distance constraints, and vertex displacement constraints. Based on this solution, we develop a fast and safe collision handling process for enforcing constraints, a novel splitting method for integrating collision handling with dynamics solvers, and static and adaptive remeshing schemes to further improve the runtime performance. In summary, our cloth simulator is efficient, safe, robust, and parallelizable on a GPU. The experiment shows that it runs at least one order of magnitude faster than existing simulators.

Most of the existing methods for 3D hand analysis based on RGB images mainly focus on estimating hand keypoints or poses, which cannot capture geometric details of the 3D hand shape. In this work, we propose a novel method to reconstruct a 3D hand mesh from a single monocular RGB image. Different from current parameter-based or pose-based methods, our proposed method directly estimates the 3D hand mesh based on graph convolution neural network (GCN). Our network consists of two modules: the hand localization and mask generation module, and the 3D hand mesh reconstruction module. The first module, which is a VGG16-based network, is applied to localize the hand region in the input image and generate the binary mask of the hand. The second module takes the high-order features from the first and uses a GCN-based network to estimate the coordinates of each vertex of the hand mesh and reconstruct the 3D hand shape. To achieve better accuracy, a novel loss based on the differential properties of the discrete mesh is proposed. We also use professional software to create a large synthetic dataset that contains both ground truth 3D hand meshes and poses for training. To handle the real-world data, we use the CycleGAN network to transform the data domain of real-world images to that of our synthesis dataset. We demonstrate that our method can produce accurate 3D hand mesh and achieve an efficient performance for real-time applications.

Since precise self-position estimation is required for autonomous flight of aerial robots, there has been some studies on self-position estimation of indoor aerial robots. In this study, we tackle the self-position estimation problem by mounting a small downward-facing camera on the chassis of an aerial robot. We obtain robot position by sensing the features on the indoor floor. In this work, we used the vertex points &#x0028 tile corners &#x0029 where four tiles on a typical tiled floor connected, as an existing feature of the floor. Furthermore, a small lightweight microcontroller is mounted on the robot to perform image processing for the on-board camera. A lightweight image processing algorithm is developed. So, the real-time image processing could be performed by the microcontroller alone which leads to conduct on-board real time tile corner detection. Furthermore, same microcontroller performs control value calculation for flight commanding. The flight commands are implemented based on the detected tile corner information. The above mentioned all devices are mounted on an actual machine, and the effectiveness of the system was investigated.

Diffs, a concept known from source code version control systems such as git, is interesting for geospatial, event-based workflows. We investigate how the native mathematical structure of vector geometries can be utilized in order to create a diffing algorithm tailored to geospatial vector data. Diffing algorithms are a well-researched area which dates to the 1970ies; however, we find that geospatial diffing operations tends to be carried out using generic algorithms combined with a pre- and post-processing step. We created GeomDiff, an algorithm and storage format tailored to geospatial vector data. The creation time, apply/undo time, and patch size of GeomDiff was compared to three other generic algorithms by running an online experiment using 2.5 million real-world geometry pairs from OpenStreetMap. We found that the GeomDiff algorithm performs better than or on-par with the alternatives on point-geometries, and complex geometries with a small (

This study presents the implementation and validation of a new sediment-scour model with a strict vertex-based, terrain conformal, moving-mesh technique within the framework of OpenFOAM. OpenFOAM lacks the ability to simulate large-amplitude motion needed for analysis of sediment-scour problems, and, thus, its application normally is restricted to small-amplitude cases to prevent computational divergence due to mesh deterioration. The proposed simple, moving-mesh technique in OpenFOAM is implemented to overcome the shortcomings of the conventional automatic mesh-motion techniques in handling large-amplitude moving geometries. The model is used to simulate a simple case of prescribed boundary motion, a previous experiment in the literature, and a new laboratory experiment for local scour due to submerged wall jets. The results are compared with both the experimental and other numerical results. The comparisons demonstrate that the proposed model has the novel advantage of allowing for more severe topographic variations, and can provide more reliable predictions for the key characteristics and evolution of the bed profiles in wall jet scour problems. Furthermore, to improve the practice of modeling wall jet scour, various turbulence modeling approaches and bedload equations also are evaluated and compared.

A geometry video is formed as a sequence of geometry images where each frame is a remeshed form of a frame of an animated mesh sequence. For efficiently coding geometry videos by exploiting temporal as well spatial correlation at multiple scales, this paper proposes the 3D-SPECK algorithm which has been successfully applied to the coding of volumetric medical image data and hyperspectral image data in the past. The paper also puts forward several postprocessing operations on the reconstructed surfaces that compensate for the visual artifacts appearing in the form of undulations due to the loss of high-frequency wavelet coefficients, cracks near geometry image boundaries due to vertex coordinate quantization errors and serrations due to regular or quad splitting triangulation of local regions of large anisotropic geometric stretch. Experimental results on several animated mesh sequences demonstrate the superiority of the subjective and objective coding performances of the newly proposed approach to those of the commonly recognized animated mesh sequence coding approaches at low and medium coding rates.

Efficient denoising is of great significance to unmixing hyperspectral images. In the present study, a fast unmixing method for noisy hyperspectral images based on the combination of vertex compone...

In the fields of computer graphics and computer vision, a great amount of research and analysis has been conducted on expression-carrying face models. How to construct more realistic and effective 3D face models has become an immense challenge to researchers. This paper proposes a parametric 3D face model editing algorithm based on existing 3D face models. The algorithm takes a number of existing 3D face models with different expressions as input, edits the models through mostly through model deformation and interpolation, and generates a new 3D face model. In particular, the face model editing process begins with selecting multiple face models with different expressions as input. Second, with one of the selected models as the source model and others as the target models, the source model and all target models are registered one by one; meanwhile, the vertex correspondence between the registered models is established. Third, the selected 3D models are parameterized to a planar disc through quasi-conformal mapping. Fourth, relying on the vertex correspondence, a set of corresponding control points between different models are established. The model is then deformed and interpolated under the guidance of the control points and by using the quasi-conformal iteration method, which produces the 2D face models with transitional expressions between the source model and the target models. Finally, the 2D models are restored to the corresponding 3D face models using the model restoration algorithm. Additionally, this paper proposes to use the Beltrami coefficient to guide the quasi-conformal iteration in performing the mapping between two planes. This coefficient then serves as a measure to evaluate the similarity between the edited model and the original one. The proposed algorithm has been evaluated through extensive experiments. The results suggest that compared with existing editing methods, the proposed method is more effective and efficient in constructing various 3D face models.

In this work, we propose a novel solution for simplifying texture-mapped three-dimensional (3D) meshes. It simplifies a 3D triangular mesh to optimally preserve the visual appearance of the original texture-mapped model at reduced vertex budgets. While taking the prevalent strategy of iterative edge contraction, the proposed scheme is novel in that it takes into account the local texture image characteristics when prioritizing local mesh simplification operators, and conducts closed-form optimization when computing the texture coordinates of each replacement vertex. Outstanding performance of the proposed scheme is demonstrated both qualitatively and quantitatively by experimental results. Further, validity of the proposed algorithmic components is well proved through ablation study.

In this paper we present an efficient GPU-based framework to dynamically perform the voxelization of polygonal models for training 3D convolutional neural networks. It is designed to manage the dataset augmentation by using efficient geometric transformations and random vertex displacements in GPU. With the proposed system, every voxelization is carried out on-the-fly for directly feeding the network. The computing performance with this approach is much better than with the standard method, that carries out every voxelization of each model separately and has much higher data processing overhead. The core voxelization algorithm works by using the standard rendering pipeline of the GPU. It generates binary voxels for both the interior and the surface of the models. Moreover, it is simple, concise and very compatible with commodity hardware, as it neither uses complex data structures nor needs vendor-specific hardware or additional dependencies. This framework dramatically reduces the input/output operations, and completely eliminates the storage footprint of the voxelization dataset, managing it as an implicit dataset.

In this paper, we proposed a novel operation to reconstruction tetrahedrons within a certain region, which we call MFRC (Multi-face reconstruction). During the existing tetrahedral mesh improvement methods, the flip operation is one of the very important components. However, due to the limited area affected by the flip, the improvement of the mesh quality by the flip operation is also very limited. The proposed MFRC algorithm solves this problem. MFRC can reconstruct the local mesh in a larger range and can find the optimal tetrahedron division in the target area within acceptable time complexity. Therefore, based on the MFRC algorithm, we combined other operations including smoothing, edge removal, face removal, and vertex insertion/deletion to develop an effective mesh quality improvement method. Numerical experiments of dozens of meshes show that the algorithm can effectively improve the low-quality elements in the tetrahedral mesh, and can effectively reduce the running time, which has important significance for the quality improvement of large-scale mesh.

In this paper, we present an efficient algorithm that generates lip-synchronized facial animation from a given vocal audio clip. By combining spectral-dimensional bidirectional long short-term memory and temporal attention mechanism, we design a light-weight speech encoder that learns useful and robust vocal features from the input audio without resorting to pre-trained speech recognition modules or large training data. To learn subject-independent facial motion, we use deformation gradients as the internal representation, which allows nuanced local motions to be better synthesized than using vertex offsets. Compared with state-of-the-art automatic-speech-recognition-based methods, our model is much smaller but achieves similar robustness and quality most of the time, and noticeably better results in certain challenging cases.

Multivariate dynamic networks indicate networks whose topology structure and vertex attributes are evolving along time. They are common in multimedia applications. Anomaly detection is one of the essential tasks in analyzing these networks though it is not well addressed. In this paper, we combine a rare category detection method and visualization techniques to help users to identify and analyze anomalies in multivariate dynamic networks. We conclude features of rare categories and two types of anomalies of rare categories. Then we present a novel rare category detection method, called DIRAD, to detect rare category candidates with anomalies. We develop a prototype system called iNet, which integrates two major visualization components, including a glyph-based rare category identifier, which helps users to identify rare categories among detected substructures, a major view, which assists users to analyze and interpret the anomalies of rare categories in network topology and vertex attributes. Evaluations, including an algorithm performance evaluation, a case study, and a user study, are conducted to test the effectiveness of proposed methods.

Aiming at the problems of the loss of model details and poor mesh quality when the mesh simplification algorithm simplifies the 3D model, a high-quality mesh simplification algorithm that maintains the characteristics is proposed. In the process of simplification of the 3D mesh model, first of all, for the loss of detailed features of the mesh model, the discrete curvature of the vertex is introduced, and it is combined with the original error matrix to maintain the simplified model to a large extent. Detailed features: After simplification, to solve the problem of poor triangle quality, Laplacian is introduced to optimize the triangular mesh, reduce the number of long and narrow triangles, and improve the quality of the triangular mesh. The proposed algorithm not only considers the geometric characteristics, but also considers the smoothness of the mesh, making the simplified model approximate to the original model. Experimental results show that the algorithm effectively retains the detailed features and mesh smoothness, and the simplification effect is better.

With the advances in cardiovascular imaging technologies in recent years, 4D (3D+time) patient-specific modeling of the heart has attracted many research interests. Computational modeling approaches such as Computational Fluid Dynamics (CFD) and Finite Element (FE) have been increasingly used to quantitatively diagnose and predict cardiovascular diseases. In these methods, the geometrical reconstruction of the heart anatomy is usually an indispensable step. This work presents a robust method for reconstructing time-varying subdivision surfaces from the segmentation masks of cardiac images. We first reconstruct a 3D mesh for the first time step by iteratively fitting an initial mesh based on error and tension terms. Each subsequent time step uses the model from its previous time step as the control mesh for subdivision surface fitting. This method preserves the 1-to-1 vertex correspondence between meshes in different time steps and allows us to control the mesh quality (i.e. resolution, smoothness, and accuracy). Furthermore, in contrast to contour-based algorithms, our method can handle non-trivial topological changes such as holes and tunnels. The method has been tested on 3D and 4D datasets of different modalities (i.e. CT and MRI), resolutions, and chambers. For creating visually appealing results, we show that synthetic textures can be mapped to the 4D reconstruction due to the vertex correspondence. We also quantitatively evaluate the reconstructed 3D meshes in terms of mesh quality and conformity to the data.

Adaptive FDTD mesh generation technique based on cuboid ray column intersection method in three-dimensional FDTD simulation is proposed in this paper. According to the vertex coordinates of the triangular patches on the object's surface, non-uniform structured mesh lines are placed. Since the placement of these mesh lines is constrained by the object geometry and wavelength, this grid lines setting method is more accurate and efficient. Then by marking the meshes determined by the intersections of cuboid ray columns and triangular patches, the discretization of complex target can be realize. The parabolic antenna is modeled to prove the validity of this novel technique.

Golf ball dimple arrangements are one of the most visible and challenging distribution of points on a sphere. The number of dimples and their spherical arrangement influence the flight and landing characteristics of balls. Some designs maximize land areas while others minimize it. Ball design is highly competitive as shown by the more than 300 patents issued by the US Patent and Trademark Office. This does count patents for surface coverings, coatings, or core make up. This chapter shows the basic designs sports ball designers are using. Spherical platonics are favored as base references and ways to meet association standards for uniform performance. Most designs attempt to maximize the number of symmetries (face, vertex, edge). Sphere packing, symmetry, and manufacturing must work together; examples show how icosahedral, octahedral, and tetrahedral designs have evolved.

In this paper, we describe the design, development and preliminary evaluation of a novel animation tool for smartphones and tablets, with the goal of improving creativity and problem-solving ability among novice users, mainly young children. The user first draws the objects with markers and crayons on paper and takes a photo with their mobile or tablet to import their drawings into the app as game sprites. They then design their animation scene and point to a part of the character and selecting its animation type from existing buttons. Hence the selected part is animated in a vertex shader while ensuring a smooth transition with the non-pointed part. The results of a preliminary evaluation showed that young children enjoyed interacting with our tool and would recommend it to their friends. Keywords and Phrases: Creativity; video games; visual animation; ease of use.

Conditional human image generation, or generation of human images with specified pose based on one or more reference images, is an inherently ill-defined problem, as there can be multiple plausible appearance for parts that are occluded in the reference. Using multiple images can mitigate this problem while boosting the performance. In this work, we introduce a differentiable vertex and edge renderer for incorporating the pose information to realize human image generation conditioned on multiple reference images. The differentiable renderer has parameters that can be jointly optimized with other parts of the system to obtain better results by learning more meaningful shape representation of human pose. We evaluate our method on the Market-1501 and DeepFashion datasets and comparison with existing approaches validates the effectiveness of our approach.

To visually label the copyright of 2D CAD (Computer aided design) engineering graphics, a reversible visible watermarking based on graphics fusion is proposed. For a given watermark graphics, the lines are first converted into polylines, and a random perturbation is performed to each vertex by using a random seed. Secondly, the host graphics are equally divided into multiple regions, and then the centers of these regions are calculated. The center of each watermark graphics is aligned with the center of each region. After that, the watermark graphics are scaled to be suitable for the size of these regions. Finally, the watermark graphics are iteratively embedded by fusing the host graphics and the watermark graphics. The host graphics can be completely recovered from the fused graphics by the authorized users who know the secret key. Experimental results validate its effectiveness, and the analysis demonstrates that it has a certain robustness against translation, rotation, scaling, and entity deletion.

In the past the Vertex Morphing method has mainly been used in the context of optimization of thin walled shell structures or fluid mechanical problems. In this paper an extension of this parameter free shape optimization method to 3-dimensional solid structures based on the free Finite Element code CalculiX is presented. Key element of the whole process is an efficient adjoint sensitivity analysis that can handle many design variables providing gradient information for the response functions of interest, e.g. stresses and mass. Typically, parameter free shape optimal designs result in non-smooth geometries and suffer from mesh dependencies. To avoid these phenomena an intermediate filter operation in combination with several post processing steps of the raw sensitivities is added. In the optimization, the filter size is also used as an additional design parameter controlling the curvature of the optimal shape. In many engineering optimization applications constraints have to be considered. These restrictions are included in the optimization problem by the use of Rosen’s gradient projection method. For the successive shape update a pseudo linear-elastic static Finite Element analysis with multiple point constraints and a varying Young’s modulus is performed in every design iteration . Finally, the capabilities of the extended Vertex Morphing method are demonstrated for an academic example and a geometrically complex part from aerospace industry.

“It’s called a BHAG,” says Hayden Thomas, divulging a term popular among chemical engineers at Vertex Pharmaceuticals, where Thomas is vice president of formulation development. “A big, hairy, auda...

Cell-based, mathematical modeling of collective cell behavior has become a prominent tool in developmental biology. Cell-based models represent individual cells as single particles or as sets of interconnected particles, and predict the collective cell behavior that follows from a set of interaction rules. In particular, vertex-based models are a popular tool for studying the mechanics of confluent, epithelial cell layers. They represent the junctions between three (or sometimes more) cells in confluent tissues as point particles, connected using structural elements that represent the cell boundaries. A disadvantage of these models is that cell-cell interfaces are represented as straight lines. This is a suitable simplification for epithelial tissues, where the interfaces are typically under tension, but this simplification may not be appropriate for mesenchymal tissues or tissues that are under compression, such that the cell-cell boundaries can buckle. In this paper we introduce a variant of VMs in which this and two other limitations of VMs have been resolved. The new model can also be seen as on off-the-lattice generalization of the Cellular Potts Model. It is an extension of the open-source package VirtualLeaf, which was initially developed to simulate plant tissue morphogenesis where cells do not move relative to one another. The present extension of VirtualLeaf introduces a new rule for cell-cell shear or sliding, from which T1 and T2 transitions emerge naturally, allowing application of VirtualLeaf to problems of animal development. We show that the updated VirtualLeaf yields different results than the traditional vertex-based models for differential-adhesion-driven cell sorting and for the neighborhood topology of soft cellular networks., Comment: 28 pages, 4 figures; accepted for publication in Bulletin of Mathematical Biology

Reversible data hiding (RDH) recover the original media without any distortion after extraction of the hidden data. Since massive three-dimensional (3D) mesh models have been constructed from high-dimensional image data nowadays, existing deficiencies of prior studies on RDH of 3D mesh models need to be overcome for performance improvement. In this paper, we propose an improved RDH method for 3D mesh models based on prediction-error expansion and sorting. Instead of considering only several adjacent neighbors, the proposed method predict a vertex position with a ring pattern for better prediction accuracy. To make better capacity-distortion control, data bits are reversibly embedded into 3D mesh models with embedding operations including expansion, shifting and LSB replacement. Moreover, we propose smoothness sorting and twice-layered strategy to enhance the embedding performance further. Thus, the proposed method achieves improved embedding performance in terms of capacity enhancement and distortion reduction. Experimental results demonstrate that the proposed method produces relatively superior results compared with previous related state-of-the-art works.

A combined method of object visualization based on analytical and scalar perturbation functions and three-dimensional textures with the use of graphics processing units is proposed. To display the terrain and the change in levels of detail, the same method as that for color textures is applied, and vertex shaders are used in the case of scattered light. A method of real-time visualization of volumetric clouds is described. For this purpose, it is proposed to form three-dimensional textures by means of pre-processing of the cloud structure and volume-oriented visualization.

For intelligent support of consruction site, it is needed to estimate the workload of excavator bucket. But, previous studies are not practical by the reason of non-real-time processing or implementation cost. In this paper, a novel method, which use only a single camera and image processing technique to estimate the workload of excavator bucket, is addressed based on the assumption of actual bucket size, uniformity of sand, and geometric model for the shape of excavator bucket and the shape of accumulated sand in the bucket. For the ease of analysis, the state of bucket was divided into three states, Under-Struck state, Struck state, and Heaped state, depending on the amount of sand accumulation. Specially, Heaped state was also divided into Sharply-Heaped state and Smoothly-Heaped state depending on the relative height of peak point of the sand pyramid in the view of photographed image. By finding the positions of bucket corner points, highest vertex of the sand pyramid and uppermost edge point of the sand region in photographed image, various geometric parameters are found by using mathematical modeling. Hereafter, the volume of sand in the bucket is estimated by using the ratio between the length of the actual bucket and the length of the bucket in the photographed image. Finally, the workload of the excavator bucket represented by the mass is obtained by multiplying the pre-defined density of sand. Experimental results show that the accuracy of the proposed method is 93.7% on average.

A randomized kinodynamic path planning algorithm based on the incremental sampling-based method is proposed here as the state-of-the-art in this field applicable in an autonomous underwater vehicle. Designing a feasible path for this vehicle from an initial position and velocity to a target position and velocity in three-dimensional spaces by considering the kinematic constraints such as obstacles avoidance and dynamic constraints such as hard bounds and non-holonomic characteristic of AUV are the main motivation of this research. For this purpose, a closed-loop rapidly-exploring random tree (CL-RRT) algorithm is presented. This CL-RRT consists of three tightly coupled components: a RRT algorithm, three fuzzy proportional-derivative controllers for heading and diving control and a six degree-of-freedom nonlinear AUV model. The branches of CL-RRT are expanded in the configuration space by considering the kinodynamic constraints of AUV. The feasibility of each branch and random offspring vertex in the CL-RRT is checked against the mentioned constraints of AUV. Next, if the planned branch is feasible by the AUV, then the control signals and related vertex are recorded through the path planner to design the final path. This proposed algorithm is implemented on a single board computer (SBC) through the xPC Target and then four test-cases are designed in 3D space. The results of the processor-in-the-loop tests are compared by the conventional RRT and indicate that the proposed CL-RRT not only in a rapid manner plans an initial path, but also the planned path is feasible by the AUV.

Despite the large work made in interactive mesh deformation, manipulating a geometrically complex mesh and producing realistic deformation result is still a challenging work. Example-driven deformation methods distinctly simplify the modeling process and produce realistic deformation result by incorporating knowledge learned from shape space. We introduce a rotation invariant feature representation and a reconstruction framework to accurately reconstruct the vertex positions. Our feature representation allows both interpolation as well as extrapolation and can effectively blend multiple shapes. Based on this, we achieve an example-driven approach to mesh deformations. By using a collection of models as examples, our method produces natural deformation results guided by them even with large movement of handles. We will apply our representation and reconstruction method to semantic deformation transfer. The experimental results have demonstrated the effectiveness of the proposed methods.

The paper proposes a conversion of plane shooting targets using twodimensional affine transformations. It is assumed that affine transformations will be useful for target generation in firearms training simulators (FATS). The structure and the matrix formation algorithm of target vertex matrices are described as well as transformation matrices and output matrices. Vertex matrices were formed for twelve plane shooting targets. Transformation matrices 3×3 in size were used for conversions. Mathematical modelling and computer simulation of software-configurable plane shooting targets for FATS were performed in the Mathcad v.15 software.

The image processing pipeline boasts a wide variety of complex filters and effects. Translating an individual effect to operate on 3D surface geometry inevitably results in a bespoke algorithm. Instead, we propose a general-purpose back-end optimization that allows users to edit an input 3D surface by simply selecting an off-the-shelf image processing filter. We achieve this by constructing a differentiable triangle mesh renderer, with which we can back propagate changes in the image domain to the 3D mesh vertex positions. The given image processing technique is applied to the entire shape via stochastic snapshots of the shape: hence, we call our method Paparazzi. We provide simple yet important design considerations to construct the Paparazzi renderer and optimization algorithms. The power of this rendering-based surface editing is demonstrated via the variety of image processing filters we apply. Each application uses an off-the-shelf implementation of an image processing method without requiring modification to the core Paparazzi algorithm.

In this paper, we consider disassembly scenarios for real-world 3D CAD-data, where each component is defined by a triangle mesh. For a fast construction of collision-free disassembly paths, common approaches use sampling-based rigid body motion planning which is well studied in the literature. One fact that has so far received little attention is that in industrial disassembly scenarios components are often attached to each other with flexible fastening elements like clips. In the planning process, the fastening elements show the following characteristics: 1) They can cause complex non-linear disassembly paths. 2) They are often deformable. 3) They are usually modeled in a relaxed state and as an unknown part of the rigid mesh. That leads to the problem that unavoidable collisions occur during the planning process. Hence, the localization of the fastening elements and the integration of this information into the motion planning process is crucial for an automatic disassembly.We present a new geometric solution to extract salient features of 3D meshes which is specialized to find the fastening elements within the otherwise rigid mesh. Our approach measures a vertex-based surface feature using a local Gauss map in combination with a local thickness computation of the mesh. We compare our surface feature to state-of-the-art mesh saliency methods on various examples. Further, we integrate this measure of per-vertex saliency into a motion planning process and demonstrate the effectiveness of our result on real-world planning scenarios from the automotive industry.