检索结果-内蒙古大学图书馆

High-resolution depth for binocular image-based modeling

COMPUTERS & GRAPHICS-UK 2014年第1期39卷 89-100页

作者： Blumenthal-Barby, David C. Eisert, Peter Fraunhofer Heinrich Hertz Inst Berlin Germany Humboldt Univ D-10099 Berlin Germany

We propose a binocular stereo method which is optimized for reconstructing surface detail and exploits the high image resolutions of current digital cameras. Our method occupies a middle ground between stereo algorithms focused on depth layering of cluttered scenes and multi-view "object reconstruction" approaches which require a higher view count. It is based on global non-linear optimization of continuous scene depth rather than discrete pixel disparities. We propose a mesh-based data-term for large images, and a smoothness term using robust error norms to allow detailed surface geometry. We show that the continuous optimization approach enables interesting extensions beyond the core algorithm: Firstly, with small changes to the data-term camera parameters instead of depth can be optimized in the same framework. Secondly, we argue that our approach is well suited for a semi-interactive reconstruction work-flow, for which we propose several tools. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： 3D reconstruction image-based modeling Optimization Interaction in 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Putting the User in the Loop for image-based modeling

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2014年第1-2期108卷 30-48页

作者： Kowdle, Adarsh Chang, Yao-Jen Gallagher, Andrew Batra, Dhruv Chen, Tsuhan Cornell Univ Ithaca NY 14853 USA Siemens Corp Corp Technol Princeton NJ USA Virginia Tech Blacksburg VA USA

We refer to the task of recovering the 3D structure of an object or a scene using 2D images as image-based modeling. In this paper, we formulate the task of recovering the 3D structure as a discrete optimization problem solved via energy minimization. In this standard framework of a Markov random field (MRF) defined over the image we present algorithms that allow the user to intuitively interact with the algorithm. We introduce an algorithm where the user guides the process of image-based modeling to find and model the object of interest by manually interacting with the nodes of the graph. We develop end user applications using this algorithm that allow object of interest 3D modeling on a mobile device and 3D printing of the object of interest. We also propose an alternate active learning algorithm that guides the user input. An initial attempt is made at reconstructing the scene without supervision. Given the reconstruction, an active learning algorithm uses intuitive cues to quantify the uncertainty of the algorithm and suggest regions, querying the user to provide support for the uncertain regions via simple scribbles. These constraints are used to update the unary and the pairwise energies that, when solved, lead to better reconstructions. We show through machine experiments and a user study that the proposed approach intelligently queries the users for constraints, and users achieve better reconstructions of the scene faster, especially for scenes with textureless surfaces lacking strong textural or structural cues that algorithms typically require.

关键词： image-based modeling Interactive 3D reconstruction Active-learning Energy minimization

来源：评论

学校读者我要写书评

暂无评论

A machine learning approach for magnetic resonance image-based mouse brain modeling and fast computation in controlled cortical impact

引用

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 2020年第11期58卷 2835-2844页

作者： Lai, Changxin Chen, Yu Wang, Tianyao Liu, Jun Wang, Qian Du, Yiping Feng, Yuan Shanghai Jiao Tong Univ Inst Med Imaging Technol Sch Biomed Engn Shanghai 200030 Peoples R China Fudan Univ Peoples Hosp Shanghai 5 Dept Radiol 801 Heqing Rd Shanghai 200240 Peoples R China

Computational modeling of the brain is crucial for the study of traumatic brain injury. An anatomically accurate model with refined details could provide the most accurate computational results. However, computational models with fine mesh details could take prolonged computation time that impedes the clinical translation of the models. Therefore, a way to construct a model with low computational cost while maintaining a computational accuracy comparable with that of the high-fidelity model is desired. In this study, we constructed magnetic resonance (MR) image-based finite element (FE) models of a mouse brain for simulations of controlled cortical impact. The anatomical details were kept by mapping each image voxel to a corresponding FE mesh element. We constructed a super-resolution neural network that could produce computational results of a refined FE model with a mesh size of 70 mu m from a coarse FE model with a mesh size of 280 mu m. The peak signal-to-noise ratio of the reconstructed results was 33.26 dB, while the computational speed was increased by 50-fold. This proof-of-concept study showed that using machine learning techniques, MR image-based computational modeling could be applied and evaluated in a timely fashion. This paved ways for fast FE modeling and computation based on MR images. Results also support the potential clinical applications of MR image-based computational modeling of the human brain in a variety of scenarios such as brain impact and intervention.

关键词： image-based modeling Mouse model Controlled cortical impact Super resolution Neural network

来源：评论

学校读者我要写书评

暂无评论

Large Scale Farm Scene modeling from Remote Sensing imagery

引用

ACM TRANSACTIONS ON GRAPHICS 2024年第6期43卷 1-12页

作者： Xiao, Zhiqi Jiang, Hao Deng, Zhigang Li, Ran Han, Wenwei Wang, Zhaoqi Univ Chinese Acad Sci Chinese Acad Sci Inst Comp Technol Beijing Peoples R China Univ Houston Dept Comp Sci Houston TX 77004 USA Univ Chinese Acad Sci Chinese Acad Sci Inst Comp Technol Beijing Peoples R China

In this paper we propose a scalable framework for large-scale farm scene modeling that utilizes remote sensing data, specifically satellite images. Our approach begins by accurately extracting and categorizing the distributions of various scene elements from satellite images into four distinct layers: fields, trees, roads, and grasslands. For each layer, we introduce a set of controllable Parametric Layout Models (PLMs). These models are capable of learning layout parameters from satellite images, enabling them to generate complex, large-scale farm scenes that closely reproduce reality across multiple scales. Additionally, our framework provides intuitive control for users to adjust layout parameters to simulate different stages of crop growth and planting patterns. This adaptability makes our model an excellent tool for graphics and virtual reality applications. Experimental results demonstrate that our approach can rapidly generate a variety of realistic and highly detailed farm scenes with minimal inputs.

关键词： image-based modeling procedural modeling farm scene modeling remote sensing images parametric layout models

来源：评论

学校读者我要写书评

暂无评论

image-based metric heritage modeling in the near-infrared spectrum

引用

HERITAGE SCIENCE 2020年第1期8卷 1-12页

作者： Adamopoulos, Efstathios Bovero, Alessandro Rinaudo, Fulvio Univ Torino Dept Comp Sci Corso Svizzera 185 I-10149 Turin TO Italy Fdn Ctr Conservaz & Restauro Beni Culturali La Ve Via 20 Settembre 18 I-10078 Venaria TO Italy Politecn Torino Dept Architecture & Design Viale Mattioli 39 I-10125 Turin Italy

Digital photogrammetry and spectral imaging are widely used in heritage sciences towards the comprehensive recording, understanding, and protection of historical artifacts and artworks. The availability of consumer-grade modified cameras for spectral acquisition, as an alternative to expensive multispectral sensors and multi-sensor apparatuses, along with semi-automatic software implementations of Structure-from-Motion (SfM) and Multiple-View-Stereo (MVS) algorithms, has made more feasible than ever the combination of those techniques. In the research presented here, the authors assess image-based modeling from near-infrared (NIR) imagery acquired with modified consumer-grade cameras, with applications on tangible heritage. Three-dimensional (3D) meshes, textured with the non-visible data, are produced and evaluated. Specifically, metric evaluations are conducted through extensive comparisons with models produced with image-based modeling from visible (VIS) imagery and with structured light scanning, to check the accuracy of results. Furthermore, the authors observe and discuss, how the implemented NIR modeling approach, affects the surface of the reconstructed models, and may counteract specific problems which arise from lighting conditions during VIS acquisition. The radiometric properties of the produced results are evaluated, in comparison to the respective results in the visible spectrum, on the capacity to enhance observation towards the characterization of the surface and under-surface state of preservation, and consequently, to support conservation interventions.

关键词： image-based modeling Photogrammetry Near-infrared imaging Modified cameras Cultural heritage survey

来源：评论

学校读者我要写书评

暂无评论

Improved 3D image segmentation for X-ray tomographic data of biaxial warp-knitted composites

引用

JOURNAL OF REINFORCED PLASTICS AND COMPOSITES 2025年第7-8期44卷 344-357页

作者： Zheng, Kehong Wu, Chenglie Chen, Hao Zhang, Xiyan Wang, Zhenyu Pan, Zhongxiang Qiu, Bingjing Wu, Zhenyu Zhejiang Sci Tech Univ Coll Mech Engn Xiasha Zhejiang Peoples R China Zhejiang Univ Coll Civil Engn & Architecture Hangzhou Peoples R China CenterSinohydro Bur 12 Co Ltd Hangzhou Zhejiang Peoples R China Zhejiang Sci Tech Univ Coll Mat & Text Hangzhou Peoples R China Zhejiang Univ Ctr Hypergrav Expt & Interdisciplinary Res Hangzhou Peoples R China

Identifying different features and phases within the biaxial warp-knitted composites enables accurate characterization of the internal changes of the composites under complex loading conditions and different processing parameters. However, obtaining 3D reconstructions that can be accurately segmented and quantitatively analyzed is still a challenge, primarily due to the low attenuation of materials, especially the low contrast between the weft yarn and warp yarns. Here, we use deep learning approaches to identify the boundary of the section of the tow on the 2D image, extract individual warp or weft tows automatically, and this is followed by computational modeling of composite materials. The results show that the performance of ResUNet++ model is better than that of other models for the biaxial warp-knitted composite specimen segmentation tasks. The special improved dataset augmentation algorithm is also a positive effective way to enhance network performance.

关键词： X-ray computed tomography (XCT) images dataset augmentation ResUNet plus plus model deep learning-based segmentation image-based modeling

来源：评论

学校读者我要写书评

暂无评论

Isogeometric multipatch surface fitting in tomographic images: Application to lattice structures

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2025年 436卷

作者： Bichet, D. Passieux, J. C. Perie, J. N. Bouclier, R. Univ Toulouse Inst Math Toulouse IMT CNRS UPSINSAUMR5219 135 Ave Rangueil F-31077 Toulouse France Univ Toulouse Inst Clement Ader ICA CNRS INSAISAEMines AlbiUPS 3 Rue Caroline Aigle F-31400 Toulouse France Inst Univ France IUF Paris France

Additive manufacturing has enabled the production of cellular architected (lattice) structures known for their exceptional mechanical performances. However, the printed components often exhibit geometric defects on a scale close to that of lattice struts, leading to significant deviations in mechanical behavior when comparing simulations based on the as-designed (defect-free) geometry with experimental tests on the as-manufactured (imperfect) geometry. In this work, we develop a method to extract an analysis-suitable CAD-based geometry from 3D scan data. We start by building a multipatch B-spline surface model of the as-designed lattice boundary, and then deform it to match its as-manufactured counterpart observed in a volumetric image. To achieve this, key contributions include a data fitting metric based on the Virtual image Correlation approach, combined with an image learning component;the integration of the membrane strain energy of the surface for regularization;the enforcement of higher continuity between patches where appropriate;an automatic estimation of the pose of the CAD object in the image;and the computation of a distance indicator map between the aligned CAD model and the as-manufactured surface. These elements enable comprehensive, accurate, and efficient measurement of geometric defects in lattice structures. Validated through various experiments, including those on a BCC lattice structure, this method achieves sub-voxel accuracy. Ultimately, it provides a compact and explicit representation of the as-manufactured geometry, maintaining the same CAD-based discretization as the initial design, and thereby facilitating quantitative defect assessment.

关键词： image-based modeling Digital twin Isogeometric analysis Active contours Virtual image correlation Multipatch B-spline

来源：评论

学校读者我要写书评

暂无评论

MVImgNet2.0: A Larger-scale Dataset of Multi-view images

引用

ACM TRANSACTIONS ON GRAPHICS 2024年第6期43卷 1-16页

作者： Han, Xiaoguang Wu, Yushuang Shi, Luyue Liu, Haolin Liao, Hongjie Qiu, Lingteng Yuan, Weihao Gu, Xiaodong Dong, Zilong Cui, Shuguang CUHKSZ SSE Shenzhen Peoples R China CUHKSZ FNii Shenzhen Peoples R China Alibaba Grp Guangzhou Peoples R China

MVImgNet is a large-scale dataset that contains multi-view images of- 220k real-world objects in 238 classes. As a counterpart of imageNet, it introduces 3D visual signals via multi-view shooting, making a soft bridge between 2D and 3D vision. This paper constructs the MVImgNet2.0 dataset that expands MVImgNet into a total of- 520k objects and 515 categories, which derives a 3D dataset with a larger scale that is more comparable to ones in the 2D domain. In addition to the expanded dataset scale and category range, MVImgNet2.0 is of a higher quality than MVImgNet owing to four new features: (i) most shoots capture 360 degrees views of the objects, which can support the learning of object reconstruction with completeness;(ii) the segmentation manner is advanced to produce foreground object masks of higher accuracy;(iii) a more powerful structure-from-motion method is adopted to derive the camera pose for each frame of a lower estimation error;(iv) higher-quality dense point clouds are reconstructed via advanced methods for objects captured in 360 degrees views, which can serve for downstream applications. Extensive experiments confirm the value of the proposed MVImgNet2.0 in boosting the performance of large 3D reconstruction models. MVImgNet2.0 will be public at ***/mvimgnet2, including multi-view images of all 520k objects, the reconstructed high-quality point clouds, and data annotation codes, hoping to inspire the broader vision community.

关键词： 3D Object Dataset 3D Object Reconstruction image-based modeling

来源：评论

学校读者我要写书评

暂无评论

image-based modeling and finite element analysis for metallic materials

引用

Keikinzoku/Journal of Japan Institute of Light Metals 2014年第11期64卷 525-532页

作者： Kuwazuru, Osamu Graduate School of Engineering University of Fukui 3-9-1 Bunkyo Fukui-shi Fukui910-8507 Japan

来源：评论

学校读者我要写书评

暂无评论

GarVerseLOD: High-Fidelity 3D Garment Reconstruction from a Single In-the-Wild image using a Dataset with Levels of Details

引用

ACM TRANSACTIONS ON GRAPHICS 2024年第6期43卷 1-12页

作者： Luo, Zhongjin Liu, Haolin Li, Chenghong Du, Wanghao Jin, Zirong Sun, Wanhu Nie, Yinyu Chen, Weikai Han, Xiaoguang CUHKSZ SSE Shenzhen Peoples R China CUHKSZ FNii Shenzhen Peoples R China Huawei Noahs Ark Lab London England Tencent Games DCC Algorithm Res Ctr Palo Alto CA USA

Neural implicit functions have brought impressive advances to the state-ofthe-art of clothed human digitization from multiple or even single images. However, despite the progress, current arts still have difficulty generalizing to unseen images with complex cloth deformation and body poses. In this work, we present GarVerseLOD, a new dataset and framework that paves the way to achieving unprecedented robustness in high-fidelity 3D garment reconstruction from a single unconstrained image. Inspired by the recent success of large generative models, we believe that one key to addressing the generalization challenge lies in the quantity and quality of 3D garment data. Towards this end, GarVerseLOD collects 6,000 high-quality cloth models with fine-grained geometry details manually created by professional artists. In addition to the scale of training data, we observe that having disentangled granularities of geometry can play an important role in boosting the generalization capability and inference accuracy of the learned model. We hence craft GarVerseLOD as a hierarchical dataset with levels of details (LOD), spanning from detail-free stylized shape to pose-blended garment with pixel-aligned details. This allows us to make this highly under- constrained problem tractable by factorizing the inference into easier tasks, each narrowed down with smaller searching space. To ensure GarVerseLOD can generalize well to in-the-wild images, we propose a novel labeling paradigm based on conditional diffusion models to generate extensive paired images for each garment model with high photorealism. We evaluate our method on a massive amount of in-the-wild images. Experimental results demonstrate that GarVerseLOD can generate standalone garment pieces with significantly better quality than prior approaches while being robust against a large variation of pose, illumination, occlusion, and deformation. Code and dataset are available at ***.

关键词： image-based modeling 3D Garment Reconstruction 3D Garment Dataset

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：