Graphical Models最新文献_第7页

An improved semi-synthetic approach for creating visual-inertial odometry datasets 一种改进的半合成方法创建视觉惯性里程计数据集

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2023-04-01 DOI: 10.1016/j.gmod.2023.101172

Sam Schofield, Andrew Bainbridge-Smith, Richard Green

{"title":"An improved semi-synthetic approach for creating visual-inertial odometry datasets","authors":"Sam Schofield, Andrew Bainbridge-Smith, Richard Green","doi":"10.1016/j.gmod.2023.101172","DOIUrl":"https://doi.org/10.1016/j.gmod.2023.101172","url":null,"abstract":"<div>Capturing outdoor visual-inertial datasets is a challenging yet vital aspect of developing robust visual-inertial odometry (VIO) algorithms. A significant hurdle is that high-accuracy-ground-truth systems (e.g., motion capture) are not practical for outdoor use. One solution is to use a “semi-synthetic” approach that combines rendered images with real IMU data. This approach can produce sequences containing challenging imagery and accurate ground truth but with less simulated data than a fully synthetic sequence. Existing methods (used by popular tools/datasets) record IMU measurements from a visual-inertial system while measuring its trajectory using motion capture, then rendering images along that trajectory. This work identifies a major flaw in that approach, specifically that using motion capture alone to estimate the pose of the robot/system results in the generation of inconsistent visual-inertial data that is not suitable for evaluating VIO algorithms. However, we show that it is possible to generate high-quality semi-synthetic data for VIO algorithm evaluation. We do so using an open-source full-batch optimisation tool to incorporate both mocap and IMU measurements when estimating the IMU’s trajectory. We demonstrate that this improved trajectory results in better consistency between the IMU data and rendered images and that the resulting data improves VIO trajectory error by 79% compared to existing methods. Furthermore, we examine the effect of visual-inertial data inconsistency (as a result of trajectory noise) on VIO performance to provide a foundation for future work targeting real-time applications.</div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"126 ","pages":"Article 101172"},"PeriodicalIF":1.7,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49882825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Volume reconstruction based on the six-direction cubic box-spline 基于六向三次盒样条的体积重建

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2023-01-01 DOI: 10.1016/j.gmod.2022.101168

Hyunjun Kim , Minho Kim

{"title":"Volume reconstruction based on the six-direction cubic box-spline","authors":"Hyunjun Kim , Minho Kim","doi":"10.1016/j.gmod.2022.101168","DOIUrl":"https://doi.org/10.1016/j.gmod.2022.101168","url":null,"abstract":"<div>We propose a new volume reconstruction technique based on the six-direction cubic box-spline <math><msub><mrow><mi>M</mi></mrow><mrow><mn>6</mn></mrow></msub></math>. <math><msub><mrow><mi>M</mi></mrow><mrow><mn>6</mn></mrow></msub></math> is <math><msup><mrow><mi>C</mi></mrow><mrow><mn>1</mn></mrow></msup></math> continuous and possesses an approximation order of three, the same as that of the tri-quadratic B-spline but with much lower degree. In fact, <math><msub><mrow><mi>M</mi></mrow><mrow><mn>6</mn></mrow></msub></math> has the lowest degree among the symmetric box-splines on <math><msup><mrow><mi>Z</mi></mrow><mrow><mn>3</mn></mrow></msup></math> with at least <math><msup><mrow><mi>C</mi></mrow><mrow><mn>1</mn></mrow></msup></math> continuity. We analyze the polynomial structure induced by the shifts of <math><msub><mrow><mi>M</mi></mrow><mrow><mn>6</mn></mrow></msub></math> and propose an efficient analytic evaluation algorithm for splines and their derivatives (gradient and Hessian) based on the high symmetry of <math><msub><mrow><mi>M</mi></mrow><mrow><mn>6</mn></mrow></msub></math>. To verify the evaluation algorithm, we implement a real-time GPU (graphics processing unit) isosurface raycaster which exhibits interactive performance (54.5 fps (frames per second) with <math><mrow><mn>24</mn><msup><mrow><mn>1</mn></mrow><mrow><mn>3</mn></mrow></msup></mrow></math> dataset on <math><mrow><mn>51</mn><msup><mrow><mn>2</mn></mrow><mrow><mn>2</mn></mrow></msup></mrow></math> framebuffer) on a modern graphics hardware. Moreover, we analyze <math><msub><mrow><mi>M</mi></mrow><mrow><mn>6</mn></mrow></msub></math> as a reconstruction filter and state that it is comparable to the tri-cubic B-spline, which possesses a higher approximation order.</div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"125 ","pages":"Article 101168"},"PeriodicalIF":1.7,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49875408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

SharpNet: A deep learning method for normal vector estimation of point cloud with sharp features SharpNet:一种用于尖锐特征点云法向量估计的深度学习方法

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2022-11-01 DOI: 10.1016/j.gmod.2022.101167

Zhaochen Zhang, Jianhui Nie, Mengjuan Yu, Xiao Liu

引用次数: 0

A data driven approach to generate realistic 3D tree barks 一个数据驱动的方法来生成现实的3D树树皮

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2022-09-01 DOI: 10.1016/j.gmod.2022.101166

Aishwarya Venkataramanan , Antoine Richard , Cédric Pradalier

引用次数: 0

ObjectFusion: Accurate object-level SLAM with neural object priors 目标融合:具有神经目标先验的精确目标级SLAM

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2022-09-01 DOI: 10.1016/j.gmod.2022.101165

Zi-Xin Zou , Shi-Sheng Huang , Tai-Jiang Mu , Yu-Ping Wang

{"title":"ObjectFusion: Accurate object-level SLAM with neural object priors","authors":"Zi-Xin Zou , Shi-Sheng Huang , Tai-Jiang Mu , Yu-Ping Wang","doi":"10.1016/j.gmod.2022.101165","DOIUrl":"10.1016/j.gmod.2022.101165","url":null,"abstract":"<div>Previous object-level Simultaneous Localization and Mapping (SLAM) approaches still fail to create high quality object-oriented 3D map in an efficient way. The main challenges come from how to represent the object shape effectively and how to apply such object representation to accurate online camera tracking efficiently. In this paper, we provide ObjectFusion as a novel object-level SLAM in static scenes which efficiently creates object-oriented 3D map with high-quality object reconstruction, by leveraging neural object priors. We propose a neural object representation with only a single encoder–decoder network to effectively express the object shape across various categories, which benefits high quality reconstruction of object instance. More importantly, we propose to convert such neural object representation as precise measurements to jointly optimize the object shape, object pose and camera pose for the final accurate 3D object reconstruction. With extensive evaluations on synthetic and real-world RGB-D datasets, we show that our ObjectFusion outperforms previous approaches, with better object reconstruction quality, using much less memory footprint, and in a more efficient way, especially at the object level.</div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"123 ","pages":"Article 101165"},"PeriodicalIF":1.7,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90153299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Construction of quasi-Bézier surfaces from boundary conditions 从边界条件构造拟bsamzier曲面

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2022-09-01 DOI: 10.1016/j.gmod.2022.101159

Yong-Xia Hao, Ting Li

引用次数: 0

A deep architecture for log-Euclidean Fisher vector end-to-end learning with application to 3D point cloud classification 一个深度架构的对数欧氏费雪向量端到端学习与应用于三维点云分类

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2022-09-01 DOI: 10.1016/j.gmod.2022.101164

Amira Chekir

{"title":"A deep architecture for log-Euclidean Fisher vector end-to-end learning with application to 3D point cloud classification","authors":"Amira Chekir","doi":"10.1016/j.gmod.2022.101164","DOIUrl":"https://doi.org/10.1016/j.gmod.2022.101164","url":null,"abstract":"<div>Point clouds are a widely used form of 3D data, which can be produced by depth sensors, such as RGB-D cameras. The classification of common elements of 3D point clouds remains an open research problem.We propose a new deep network approach for the end-to-end training of log-Euclidean Fisher vectors (LE-FVs), applied to the classification of 3D point clouds. Our method uses a log-Euclidean (LE) metric in order to extend the concept of Fisher vectors (FVs) to LE-FV encoding. The LE-FV was computed on covariance matrices of local 3D point cloud descriptors, representing multiple features. Our architecture is composed of two blocks. The first one aims to map the covariance matrices representing the 3D point cloud descriptors to the Euclidean space. The second block allows for joint and simultaneous learning of LE-FV Gaussian Mixture Model (GMM) parameters, LE-FV dimensionality reduction, and multi-label classification.Our LE-FV deep learning model is more accurate than the FV deep learning architecture. Additionally, the introduction of joint learning of 3D point cloud features in the log-Euclidean space, including LE-FV GMM parameters, LE-FV dimensionality reduction, and multi-label classification greatly improves the accuracy of classification. Our method has also been compared with the most popular methods in the literature for 3D point cloud classification, and it achieved good performance. The quantitative evidence will be shown through different experiments.</div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"123 ","pages":"Article 101164"},"PeriodicalIF":1.7,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91718989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Deep functional maps for simultaneously computing direct and symmetric correspondences of 3D shapes 用于同时计算三维形状的直接和对称对应的深度功能映射

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2022-09-01 DOI: 10.1016/j.gmod.2022.101163

Hui Wang , Bitao Ma , Junjie Cao , Xiuping Liu , Hui Huang

{"title":"Deep functional maps for simultaneously computing direct and symmetric correspondences of 3D shapes","authors":"Hui Wang , Bitao Ma , Junjie Cao , Xiuping Liu , Hui Huang","doi":"10.1016/j.gmod.2022.101163","DOIUrl":"https://doi.org/10.1016/j.gmod.2022.101163","url":null,"abstract":"<div>We introduce a novel method of isometric correspondences for 3D shapes, designed to address the problem of multiple solutions associated with deep functional maps when matching shapes with left-to-right reflectional intrinsic symmetries. Unlike the existing methods that only find the direct correspondences using single Siamese network, our proposed method is able to detect both the direct and symmetric correspondences among shapes simultaneously. Furthermore, our method detects the reflectional intrinsic symmetry of each shape. Key to our method is the using of two Siamese networks that learn consistent direct descriptors and their symmetric ones, combined with carefully designed regularized functional maps and supervised loss. This leads to the first deep functional map capable of both producing two high-quality correspondences of shapes and detecting the left-to-right reflectional intrinsic symmetry of each shape. Extensive experiments demonstrate that the proposed method obtains more accurate results than state-of-the-art methods for shape correspondences and reflectional intrinsic symmetries detection.</div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"123 ","pages":"Article 101163"},"PeriodicalIF":1.7,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91718990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Patch-based mesh inpainting via low rank recovery 基于补丁的网格绘制通过低等级恢复

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2022-07-01 DOI: 10.1016/j.gmod.2022.101139

Xiaoqun Wu, Xiaoyun Lin, Nan Li, Haisheng Li

引用次数: 2

Out-of-core outlier removal for large-scale indoor point clouds 大规模室内点云的核外离群值去除

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2022-07-01 DOI: 10.1016/j.gmod.2022.101142

Linlin Ge, Jieqing Feng

引用次数: 0