arXiv - CS - Graphics最新文献_第10页

FreeShell: A Context-Free 4D Printing Technique for Fabricating Complex 3D Triangle Mesh Shells FreeShell：用于制造复杂三维三角网格壳体的无上下文 4D 打印技术

arXiv - CS - Graphics Pub Date : 2024-07-28 DOI: arxiv-2407.19533

Chao Yuan, Nan Cao, Xuejiao Ma, Shengqi Dang

{"title":"FreeShell: A Context-Free 4D Printing Technique for Fabricating Complex 3D Triangle Mesh Shells","authors":"Chao Yuan, Nan Cao, Xuejiao Ma, Shengqi Dang","doi":"arxiv-2407.19533","DOIUrl":"https://doi.org/arxiv-2407.19533","url":null,"abstract":"Freeform thin-shell surfaces are critical in various fields, but their\u0000fabrication is complex and costly. Traditional methods are wasteful and require\u0000custom molds, while 3D printing needs extensive support structures and\u0000post-processing. Thermoshrinkage actuated 4D printing is an effective method\u0000through flat structures fabricating 3D shell. However, existing research faces\u0000issues related to precise deformation and limited robustness. Addressing these\u0000issues is challenging due to three key factors: (1) Difficulty in finding a\u0000universal method to control deformation across different materials; (2)\u0000Variability in deformation influenced by factors such as printing speed, layer\u0000thickness, and heating temperature; (3) Environmental factors affecting the\u0000deformation process. To overcome these challenges, we introduce FreeShell, a\u0000robust 4D printing technique that uses thermoshrinkage to create precise 3D\u0000shells. This method prints triangular tiles connected by shrinkable connectors\u0000from a single material. Upon heating, the connectors shrink, moving the tiles\u0000to form the desired 3D shape, simplifying fabrication and reducing material and\u0000environment dependency. An optimized algorithm for flattening 3D meshes ensures\u0000precision in printing. FreeShell demonstrates its effectiveness through various\u0000examples and experiments, showcasing accuracy, robustness, and strength,\u0000representing advancement in fabricating complex freeform surfaces.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141863853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

WindPoly: Polygonal Mesh Reconstruction via Winding Numbers WindPoly：通过缠绕数重建多边形网格

arXiv - CS - Graphics Pub Date : 2024-07-27 DOI: arxiv-2407.19208

Xin He, Chenlei Lv, Pengdi Huang, Hui Huang

{"title":"WindPoly: Polygonal Mesh Reconstruction via Winding Numbers","authors":"Xin He, Chenlei Lv, Pengdi Huang, Hui Huang","doi":"arxiv-2407.19208","DOIUrl":"https://doi.org/arxiv-2407.19208","url":null,"abstract":"Polygonal mesh reconstruction of a raw point cloud is a valuable topic in the\u0000field of computer graphics and 3D vision. Especially to 3D architectural\u0000models, polygonal mesh provides concise expressions for fundamental geometric\u0000structures while effectively reducing data volume. However, there are some\u0000limitations of traditional reconstruction methods: normal vector dependency,\u0000noisy points and defective parts sensitivity, and internal geometric structure\u0000lost, which reduce the practicality in real scene. In this paper, we propose a\u0000robust and efficient polygonal mesh reconstruction method to address the issues\u0000in architectural point cloud reconstruction task. It is an iterative adaptation\u0000process to detect planar shapes from scattered points. The initial structural\u0000polygonal mesh can be established in the constructed convex polyhedral space\u0000without assistance of normal vectors. Then, we develop an efficient\u0000polygon-based winding number strategy to orient polygonal mesh with global\u0000consistency. The significant advantage of our method is to provide a structural\u0000reconstruction for architectural point clouds and avoid point-based normal\u0000vector analysis. It effectively improves the robustness to noisy points and\u0000defective parts. More geometric details can be preserved in the reconstructed\u0000polygonal mesh. Experimental results show that our method can reconstruct\u0000concise, oriented and faithfully polygonal mesh that are better than results of\u0000state-of-the-art methods. More results and details can be found on\u0000https://vcc.tech/research/2024/WindPoly","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141863983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

NARVis: Neural Accelerated Rendering for Real-Time Scientific Point Cloud Visualization NARVis：用于实时科学点云可视化的神经加速渲染技术

arXiv - CS - Graphics Pub Date : 2024-07-26 DOI: arxiv-2407.19097

Srinidhi Hegde, Kaur Kullman, Thomas Grubb, Leslie Lait, Stephen Guimond, Matthias Zwicker

{"title":"NARVis: Neural Accelerated Rendering for Real-Time Scientific Point Cloud Visualization","authors":"Srinidhi Hegde, Kaur Kullman, Thomas Grubb, Leslie Lait, Stephen Guimond, Matthias Zwicker","doi":"arxiv-2407.19097","DOIUrl":"https://doi.org/arxiv-2407.19097","url":null,"abstract":"Exploring scientific datasets with billions of samples in real-time\u0000visualization presents a challenge - balancing high-fidelity rendering with\u0000speed. This work introduces a novel renderer - Neural Accelerated Renderer\u0000(NAR), that uses the neural deferred rendering framework to visualize\u0000large-scale scientific point cloud data. NAR augments a real-time point cloud\u0000rendering pipeline with high-quality neural post-processing, making the\u0000approach ideal for interactive visualization at scale. Specifically, we train a\u0000neural network to learn the point cloud geometry from a high-performance\u0000multi-stream rasterizer and capture the desired postprocessing effects from a\u0000conventional high-quality renderer. We demonstrate the effectiveness of NAR by\u0000visualizing complex multidimensional Lagrangian flow fields and photometric\u0000scans of a large terrain and compare the renderings against the\u0000state-of-the-art high-quality renderers. Through extensive evaluation, we\u0000demonstrate that NAR prioritizes speed and scalability while retaining high\u0000visual fidelity. We achieve competitive frame rates of $>$ 126 fps for\u0000interactive rendering of $>$ 350M points (i.e., an effective throughput of $>$\u000044 billion points per second) using $sim$12 GB of memory on RTX 2080 Ti GPU.\u0000Furthermore, we show that NAR is generalizable across different point clouds\u0000with similar visualization needs and the desired post-processing effects could\u0000be obtained with substantial high quality even at lower resolutions of the\u0000original point cloud, further reducing the memory requirements.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141863985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

3D Hole Filling using Deep Learning Inpainting 利用深度学习绘制 3D 填充孔洞

arXiv - CS - Graphics Pub Date : 2024-07-25 DOI: arxiv-2407.17896

Marina Hernández-Bautista, F. J. Melero

{"title":"3D Hole Filling using Deep Learning Inpainting","authors":"Marina Hernández-Bautista, F. J. Melero","doi":"arxiv-2407.17896","DOIUrl":"https://doi.org/arxiv-2407.17896","url":null,"abstract":"The current work presents a novel methodology for completing 3D surfaces\u0000produced from 3D digitization technologies in places where there is a scarcity\u0000of meaningful geometric data. Incomplete or missing data in these\u0000three-dimensional (3D) models can lead to erroneous or flawed renderings,\u0000limiting their usefulness in a variety of applications such as visualization,\u0000geometric computation, and 3D printing. Conventional surface estimation\u0000approaches often produce implausible results, especially when dealing with\u0000complex surfaces. To address this issue, we propose a technique that\u0000incorporates neural network-based 2D inpainting to effectively reconstruct 3D\u0000surfaces. Our customized neural networks were trained on a dataset containing\u0000over 1 million curvature images. These images show the curvature of vertices as\u0000planar representations in 2D. Furthermore, we used a coarse-to-fine surface\u0000deformation technique to improve the accuracy of the reconstructed pictures and\u0000assure surface adaptability. This strategy enables the system to learn and\u0000generalize patterns from input data, resulting in the development of precise\u0000and comprehensive three-dimensional surfaces. Our methodology excels in the\u0000shape completion process, effectively filling complex holes in\u0000three-dimensional surfaces with a remarkable level of realism and precision.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141769498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Uncertainty Visualization of Critical Points of 2D Scalar Fields for Parametric and Nonparametric Probabilistic Models 参数和非参数概率模型的二维标量场临界点的不确定性可视化

arXiv - CS - Graphics Pub Date : 2024-07-25 DOI: arxiv-2407.18015

Tushar M. Athawale, Zhe Wang, David Pugmire, Kenneth Moreland, Qian Gong, Scott Klasky, Chris R. Johnson, Paul Rosen

{"title":"Uncertainty Visualization of Critical Points of 2D Scalar Fields for Parametric and Nonparametric Probabilistic Models","authors":"Tushar M. Athawale, Zhe Wang, David Pugmire, Kenneth Moreland, Qian Gong, Scott Klasky, Chris R. Johnson, Paul Rosen","doi":"arxiv-2407.18015","DOIUrl":"https://doi.org/arxiv-2407.18015","url":null,"abstract":"This paper presents a novel end-to-end framework for closed-form computation\u0000and visualization of critical point uncertainty in 2D uncertain scalar fields.\u0000Critical points are fundamental topological descriptors used in the\u0000visualization and analysis of scalar fields. The uncertainty inherent in data\u0000(e.g., observational and experimental data, approximations in simulations, and\u0000compression), however, creates uncertainty regarding critical point positions.\u0000Uncertainty in critical point positions, therefore, cannot be ignored, given\u0000their impact on downstream data analysis tasks. In this work, we study\u0000uncertainty in critical points as a function of uncertainty in data modeled\u0000with probability distributions. Although Monte Carlo (MC) sampling techniques\u0000have been used in prior studies to quantify critical point uncertainty, they\u0000are often expensive and are infrequently used in production-quality\u0000visualization software. We, therefore, propose a new end-to-end framework to\u0000address these challenges that comprises a threefold contribution. First, we\u0000derive the critical point uncertainty in closed form, which is more accurate\u0000and efficient than the conventional MC sampling methods. Specifically, we\u0000provide the closed-form and semianalytical (a mix of closed-form and MC\u0000methods) solutions for parametric (e.g., uniform, Epanechnikov) and\u0000nonparametric models (e.g., histograms) with finite support. Second, we\u0000accelerate critical point probability computations using a parallel\u0000implementation with the VTK-m library, which is platform portable. Finally, we\u0000demonstrate the integration of our implementation with the ParaView software\u0000system to demonstrate near-real-time results for real datasets.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141769501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Topology-Preserving Downsampling of Binary Images 二值图像的拓扑保护下采样

arXiv - CS - Graphics Pub Date : 2024-07-25 DOI: arxiv-2407.17786

Chia-Chia Chen, Chi-Han Peng

引用次数: 0

Drawing ellipses and elliptical arcs with piecewise cubic Bézier curve approximations 用片断三次贝塞尔曲线近似法绘制椭圆和椭圆弧

arXiv - CS - Graphics Pub Date : 2024-07-24 DOI: arxiv-2407.17675

Jerry R. Van Aken

引用次数: 0

Cascaded Light Propagation Volumes using Spherical Radial Basis Functions 使用球面径向基函数的级联光传播卷

arXiv - CS - Graphics Pub Date : 2024-07-24 DOI: arxiv-2407.17336

Ludovic Silvestre, João Pereira

引用次数: 0

EUFormer: Learning Driven 3D Spine Deformity Assessment with Orthogonal Optical Images EUFormer：利用正交光学图像进行学习驱动的三维脊柱畸形评估

arXiv - CS - Graphics Pub Date : 2024-07-24 DOI: arxiv-2407.16942

Nan Meng, Jason P. Y. Cheung, Tao Huang, Moxin Zhao, Yue Zhang, Chenxi Yu, Chang Shi, Teng Zhang

{"title":"EUFormer: Learning Driven 3D Spine Deformity Assessment with Orthogonal Optical Images","authors":"Nan Meng, Jason P. Y. Cheung, Tao Huang, Moxin Zhao, Yue Zhang, Chenxi Yu, Chang Shi, Teng Zhang","doi":"arxiv-2407.16942","DOIUrl":"https://doi.org/arxiv-2407.16942","url":null,"abstract":"In clinical settings, the screening, diagnosis, and monitoring of adolescent\u0000idiopathic scoliosis (AIS) typically involve physical or radiographic\u0000examinations. However, physical examinations are subjective, while radiographic\u0000examinations expose patients to harmful radiation. Consequently, we propose a\u0000pipeline that can accurately determine scoliosis severity. This pipeline\u0000utilizes posteroanterior (PA) and lateral (LAT) RGB images as input to generate\u0000spine curve maps, which are then used to reconstruct the three-dimensional (3D)\u0000spine curve for AIS severity grading. To generate the 2D spine curves\u0000accurately and efficiently, we further propose an Efficient U-shape transFormer\u0000(EUFormer) as the generator. It can efficiently utilize the learned feature\u0000across channels, therefore producing consecutive spine curves from both PA and\u0000LAT views. Experimental results demonstrate superior performance of EUFormer on\u0000spine curve generation against other classical U-shape models. This finding\u0000demonstrates that the proposed method for grading the severity of AIS, based on\u0000a 3D spine curve, is more accurate when compared to using a 2D spine curve.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141769504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The impact of differences in facial features between real speakers and 3D face models on synthesized lip motions 真实说话者与 3D 人脸模型之间的面部特征差异对合成嘴唇动作的影响

arXiv - CS - Graphics Pub Date : 2024-07-24 DOI: arxiv-2407.17253

Rabab Algadhy, Yoshihiko Gotoh, Steve Maddock

{"title":"The impact of differences in facial features between real speakers and 3D face models on synthesized lip motions","authors":"Rabab Algadhy, Yoshihiko Gotoh, Steve Maddock","doi":"arxiv-2407.17253","DOIUrl":"https://doi.org/arxiv-2407.17253","url":null,"abstract":"Lip motion accuracy is important for speech intelligibility, especially for\u0000users who are hard of hearing or second language learners. A high level of\u0000realism in lip movements is also required for the game and film production\u0000industries. 3D morphable models (3DMMs) have been widely used for facial\u0000analysis and animation. However, factors that could influence their use in\u0000facial animation, such as the differences in facial features between recorded\u0000real faces and animated synthetic faces, have not been given adequate\u0000attention. This paper investigates the mapping between real speakers and\u0000similar and non-similar 3DMMs and the impact on the resulting 3D lip motion.\u0000Mouth height and mouth width are used to determine face similarity. The results\u0000show that mapping 2D videos of real speakers with low mouth heights to 3D heads\u0000that correspond to real speakers with high mouth heights, or vice versa,\u0000generates less good 3D lip motion. It is thus important that such a mismatch is\u0000considered when using a 2D recording of a real actor's lip movements to control\u0000a 3D synthetic character.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141769500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0