Graphical Models最新文献_第8页

Automated generation of floorplans with non-rectangular rooms 自动生成非矩形房间的平面图

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2023-05-01 DOI: 10.1016/j.gmod.2023.101175

Krishnendra Shekhawat, Rohit Lohani, Chirag Dasannacharya, Sumit Bisht, Sujay Rastogi

引用次数: 2

Camera distance helps 3D hand pose estimated from a single RGB image 相机距离有助于从单个RGB图像估计3D手姿势

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2023-05-01 DOI: 10.1016/j.gmod.2023.101179

Yuan Cui , Moran Li , Yuan Gao , Changxin Gao , Fan Wu , Hao Wen , Jiwei Li , Nong Sang

{"title":"Camera distance helps 3D hand pose estimated from a single RGB image","authors":"Yuan Cui , Moran Li , Yuan Gao , Changxin Gao , Fan Wu , Hao Wen , Jiwei Li , Nong Sang","doi":"10.1016/j.gmod.2023.101179","DOIUrl":"https://doi.org/10.1016/j.gmod.2023.101179","url":null,"abstract":"<div>Most existing methods for RGB hand pose estimation use root-relative 3D coordinates for supervision. However, such supervision neglects the distance between the camera and the object (i.e., the hand). The camera distance is especially important under a perspective camera, which controls the depth-dependent scaling of the perspective projection. As a result, the same hand pose, with different camera distances can be projected into different 2D shapes by the same perspective camera. Neglecting such important information results in ambiguities in recovering 3D poses from 2D images. In this article, we propose a camera projection learning module (CPLM) that uses the scale factor contained in the camera distance to associate 3D hand pose with 2D UV coordinates, which facilities to further optimize the accuracy of the estimated hand joints. Specifically, following the previous work, we use a two-stage RGB-to-2D and 2D-to-3D method to estimate 3D hand pose and embed a graph convolutional network in the second stage to leverage the information contained in the complex non-Euclidean structure of 2D hand joints. Experimental results demonstrate that our proposed method surpasses state-of-the-art methods on the benchmark dataset RHD and obtains competitive results on the STB and D+O datasets.</div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"127 ","pages":"Article 101179"},"PeriodicalIF":1.7,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49702994","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

High-fidelity point cloud completion with low-resolution recovery and noise-aware upsampling 具有低分辨率恢复和噪声感知上采样的高保真点云完成

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2023-04-01 DOI: 10.1016/j.gmod.2023.101173

Ren-Wu Li , Bo Wang , Lin Gao , Ling-Xiao Zhang , Chun-Peng Li

{"title":"High-fidelity point cloud completion with low-resolution recovery and noise-aware upsampling","authors":"Ren-Wu Li , Bo Wang , Lin Gao , Ling-Xiao Zhang , Chun-Peng Li","doi":"10.1016/j.gmod.2023.101173","DOIUrl":"https://doi.org/10.1016/j.gmod.2023.101173","url":null,"abstract":"<div>Completing an unordered partial point cloud is a challenging task. Existing approaches that rely on decoding a latent feature to recover the complete shape, often lead to the completed point cloud being over-smoothing, losing details, and noisy. Instead of decoding a whole shape, we propose to decode and refine a low-resolution (low-res) point cloud first, and then perform a patch-wise noise-aware upsampling rather than interpolating the whole sparse point cloud at once, which tends to lose details. Regarding the possibility of lacking details of the initially decoded low-res point cloud, we propose an iterative refinement to recover the geometric details and a symmetrization process to preserve the trustworthy information from the input partial point cloud. After obtaining a sparse and complete point cloud, we propose a patch-wise upsampling strategy. Patch-based upsampling allows to recover fine details better rather than decoding a whole shape. The patch extraction approach is to generate training patch pairs between the sparse and ground-truth point clouds with an outlier removal step to suppress the noisy points from the sparse point cloud. Together with the low-res recovery, our whole pipeline can achieve high-fidelity point cloud completion. Comprehensive evaluations are provided to demonstrate the effectiveness of the proposed method and its components.</div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"126 ","pages":"Article 101173"},"PeriodicalIF":1.7,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49882826","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: 3

Procedural generation of semantically plausible small-scale towns 语义上合理的小规模城镇的程序生成

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2023-04-01 DOI: 10.1016/j.gmod.2023.101170

Abdullah Bulbul

引用次数: 0

Learning-based 3D imaging from single structured-light image 基于学习的单结构光图像三维成像

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2023-04-01 DOI: 10.1016/j.gmod.2023.101171

Andrew-Hieu Nguyen , Olivia Rees , Zhaoyang Wang

引用次数: 5

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