Graphical Models最新文献_第10页

Graph-PBN: Graph-based parallel branch network for efficient point cloud learning 图- pbn:高效点云学习的基于图的并行分支网络

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2022-01-01 DOI: 10.1016/j.gmod.2021.101120

Cheng Zhang, Hao Chen, Haocheng Wan, Ping Yang, Zizhao Wu

{"title":"Graph-PBN: Graph-based parallel branch network for efficient point cloud learning","authors":"Cheng Zhang, Hao Chen, Haocheng Wan, Ping Yang, Zizhao Wu","doi":"10.1016/j.gmod.2021.101120","DOIUrl":"https://doi.org/10.1016/j.gmod.2021.101120","url":null,"abstract":"<div><p><span><span><span>In recent years, approaches based on graph convolutional networks (GCNs) have achieved state-of-the-art performance in point cloud learning. The typical pipeline of GCNs is modeled as a two-stage learning process: </span>graph construction and </span>feature learning<span>. We argue that such process exhibits low efficiency because a high percentage of the total time is consumed during the graph construction process when a large amount of sparse data are required to be accessed rather than on actual feature learning. To alleviate this problem, we propose a graph-based parallel branch network (Graph-PBN) that introduces a parallel branch structure to point cloud learning in this study. In particular, Graph-PBN is composed of two branches: the PointNet branch and the GCN branch. PointNet exhibits advantages in memory access and computational cost, while GCN behaves better in local context modeling. The two branches are combined in our architecture to utilize the potential of PointNet and GCN fully, facilitating the achievement of efficient and accurate recognition results. To better aggregate the features of each node in GCN, we investigate a novel operator, called EAGConv, to augment their local context by fully utilizing geometric and semantic features in a local graph. We conduct experiments on several benchmark datasets, and experiment results validate the significant performance of our method compared with other state-of-the-art approaches. Our code will be made publicly available at </span></span><span>https://github.com/zhangcheng828/Graph-PBN</span><svg><path></path></svg>.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"119 ","pages":"Article 101120"},"PeriodicalIF":1.7,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91725397","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

Authoring multi-style terrain with global-to-local control 使用全局到局部的控制来创建多样式的地形

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2022-01-01 DOI: 10.1016/j.gmod.2021.101122

Jian Zhang , Chen Li , Peichi Zhou , Changbo Wang , Gaoqi He , Hong Qin

{"title":"Authoring multi-style terrain with global-to-local control","authors":"Jian Zhang , Chen Li , Peichi Zhou , Changbo Wang , Gaoqi He , Hong Qin","doi":"10.1016/j.gmod.2021.101122","DOIUrl":"https://doi.org/10.1016/j.gmod.2021.101122","url":null,"abstract":"<div><p><span>The appearance styles of natural terrains vary significantly from region to region in real world, and there is a strong need to effectively produce realistic terrain with certain style in computer graphics<span><span>. In this paper, we advocate a novel neural network approach to the rapid synthesis of multi-style terrains that could directly learn and infer from real terrain data. The key idea is to explicitly devise a conditional </span>generative adversarial network (GAN) which encourages and favors the maximum-distance embedding of acquired styles in the latent space. Towards this functionality, we first collect a dataset that exhibits apparent terrain style diversity in their style attributes. Second, we design multiple </span></span>discriminators<span> that can distinguish different terrain styles. Third, we employ discriminators to extract terrain features in different spatial scales, so that the developed generator can produce new terrains by fusing the finer-scale and coarser-scale styles. In our experiments, we collect 10 typical terrain datasets from real terrain data that cover a wide range of regions. Our approach successfully generates realistic terrains with global-to-local style control. The experimental results have confirmed our neural network can produce natural terrains with high fidelity, which are user-friendly to style interpolation and style mixing for the terrain authoring task.</span></p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"119 ","pages":"Article 101122"},"PeriodicalIF":1.7,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91764503","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: 4

Wrinkle and curl distortion of leaves using plant dynamic 利用植物动态分析叶片的皱折和卷曲变形

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2021-11-01 DOI: 10.1016/j.gmod.2021.101118

Xiaopeng Sun , Jia Fu , Teng Chen , Yu Dong

引用次数: 1

An optimal triangle projector with prescribed area and orientation, application to position-based dynamics 一个最佳的三角形投影仪规定的面积和方向，应用于基于位置的动态

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2021-11-01 DOI: 10.1016/j.gmod.2021.101117

Carlos Arango Duque, Adrien Bartoli

{"title":"An optimal triangle projector with prescribed area and orientation, application to position-based dynamics","authors":"Carlos Arango Duque, Adrien Bartoli","doi":"10.1016/j.gmod.2021.101117","DOIUrl":"10.1016/j.gmod.2021.101117","url":null,"abstract":"<div><p>The vast majority of mesh-based modelling applications iteratively transform the mesh vertices under prescribed geometric conditions. This occurs in particular in methods cycling through the constraint set such as Position-Based Dynamics (PBD). A common case is the approximate local area preservation of triangular 2D meshes under external editing constraints. At the constraint level, this yields the nonconvex optimal triangle projection under prescribed area problem, for which there does not currently exist a direct solution method. In current PBD implementations, the area preservation constraint is linearised. The solution comes out through the iterations, without a guarantee of optimality, and the process may fail for degenerate inputs where the vertices are colinear or colocated. We propose a closed-form solution method and its numerically robust algebraic implementation. Our method handles degenerate inputs through a two-case analysis of the problem’s generic ambiguities. We show in a series of experiments in area-based 2D mesh editing that using optimal projection in place of area constraint linearisation in PBD speeds up and stabilises convergence.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"118 ","pages":"Article 101117"},"PeriodicalIF":1.7,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.gmod.2021.101117","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82892493","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

TopoKnit: A Process-Oriented Representation for Modeling the Topology of Yarns in Weft-Knitted Textiles 拓扑单元:一种面向过程的纬编织物纱线拓扑建模方法

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2021-11-01 DOI: 10.1016/j.gmod.2021.101114

Levi Kapllani , Chelsea Amanatides , Genevieve Dion , Vadim Shapiro , David E. Breen

{"title":"TopoKnit: A Process-Oriented Representation for Modeling the Topology of Yarns in Weft-Knitted Textiles","authors":"Levi Kapllani , Chelsea Amanatides , Genevieve Dion , Vadim Shapiro , David E. Breen","doi":"10.1016/j.gmod.2021.101114","DOIUrl":"10.1016/j.gmod.2021.101114","url":null,"abstract":"<div><p>Machine knitted textiles are complex multi-scale material structures increasingly important in many industries, including consumer products, architecture, composites, medical, and military. Computational modeling<span>, simulation, and design of industrial fabrics require efficient representations of the spatial, material, and physical properties of such structures. We propose a process-oriented representation, TopoKnit, that defines a foundational data structure for representing the topology of weft-knitted textiles at the yarn scale. Process space serves as an intermediary between the machine and fabric spaces, and supports a concise, computationally efficient evaluation approach based on on-demand, near constant-time queries. In this paper, we define the properties of the process space, and design a data structure to represent it and algorithms to evaluate it. We demonstrate the effectiveness of the representation scheme by providing results of evaluations of the data structure in support of common topological operations in the fabric space.</span></p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"118 ","pages":"Article 101114"},"PeriodicalIF":1.7,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.gmod.2021.101114","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88984406","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: 9

Single Image Tree Reconstruction via Adversarial Network 基于对抗网络的单幅图像树重建

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2021-09-01 DOI: 10.1016/j.gmod.2021.101115

Zhihao Liu , Kai Wu , Jianwei Guo , Yunhai Wang , Oliver Deussen , Zhanglin Cheng

引用次数: 11

Scale-Adaptive ICP Scale-Adaptive ICP

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2021-07-01 DOI: 10.1016/j.gmod.2021.101113

Yusuf Sahillioğlu , Ladislav Kavan

引用次数: 7

Combining convex hull and directed graph for fast and accurate ellipse detection 结合凸包和有向图实现快速准确的椭圆检测

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2021-07-01 DOI: 10.1016/j.gmod.2021.101110

Zeyu Shen , Mingyang Zhao , Xiaohong Jia , Yuan Liang , Lubin Fan , Dong-Ming Yan

{"title":"Combining convex hull and directed graph for fast and accurate ellipse detection","authors":"Zeyu Shen , Mingyang Zhao , Xiaohong Jia , Yuan Liang , Lubin Fan , Dong-Ming Yan","doi":"10.1016/j.gmod.2021.101110","DOIUrl":"10.1016/j.gmod.2021.101110","url":null,"abstract":"<div><p><span>Detecting ellipses<span> from images is a fundamental task in many computer vision applications. However, due to the complexity of real-world scenarios, it is still a challenge to detect ellipses accurately and efficiently. In this paper, we propose a novel method to tackle this problem based on the fast computation of </span></span><span><em>convex hull</em></span> and <span><em>directed graph</em></span><span>, which achieves promising results on both accuracy and efficiency. We use Depth-First-Search to extract branch-free curves after adaptive edge detection. Line segments are used to represent the curvature characteristic of the curves, followed by splitting at sharp corners and inflection points<span> to attain smooth arcs. Then the convex hull is constructed, together with the distance, length, and direction constraints, to find co-elliptic arc pairs. Arcs and their connectivity are encoded into a sparse directed graph, and then ellipses are generated via a fast access of the adjacency list<span>. Finally, salient ellipses are selected subject to strict verification and weighted clustering. Extensive experiments are conducted on eight real-world datasets (six publicly available and two built by ourselves), as well as five synthetic datasets. Our method achieves the overall highest F-measure with competitive speed compared to representative state-of-the-art methods.</span></span></span></p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"116 ","pages":"Article 101110"},"PeriodicalIF":1.7,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.gmod.2021.101110","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78297964","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: 7

Adaptive geometric sound propagation based on A-weighting variance measure 基于a加权方差测度的自适应几何声传播

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2021-07-01 DOI: 10.1016/j.gmod.2021.101109

Hongyang Zhou, Zhong Ren, Kun Zhou

引用次数: 2

VGF-Net: Visual-Geometric fusion learning for simultaneous drone navigation and height mapping VGF-Net:用于无人机导航和高度映射的视觉几何融合学习

IF 1.7 4区计算机科学

Graphical Models Pub Date : 2021-07-01 DOI: 10.1016/j.gmod.2021.101108

Yilin Liu, Ke Xie, Hui Huang

{"title":"VGF-Net: Visual-Geometric fusion learning for simultaneous drone navigation and height mapping","authors":"Yilin Liu, Ke Xie, Hui Huang","doi":"10.1016/j.gmod.2021.101108","DOIUrl":"10.1016/j.gmod.2021.101108","url":null,"abstract":"<div><p><span>The drone navigation requires the comprehensive understanding of both visual and geometric information in the 3D world. In this paper, we present a </span><em>Visual-Geometric Fusion Network</em><span> (VGF-Net), a deep network for the fusion analysis of visual/geometric data and the construction of 2.5D height maps for simultaneous drone navigation in novel environments. Given an initial rough height map and a sequence of RGB images, our VGF-Net extracts the visual information of the scene, along with a sparse set of 3D keypoints that capture the geometric relationship between objects in the scene. Driven by the data, VGF-Net adaptively fuses visual and geometric information, forming a unified </span><em>Visual-Geometric Representation</em>. This representation is fed to a new <em>Directional Attention Model</em> (DAM), which helps enhance the visual-geometric object relationship and propagates the informative data to dynamically refine the height map and the corresponding keypoints. An entire end-to-end information fusion and mapping system is formed, demonstrating remarkable robustness and high accuracy on the autonomous drone navigation across complex indoor and large-scale outdoor scenes.</p></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"116 ","pages":"Article 101108"},"PeriodicalIF":1.7,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.gmod.2021.101108","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81693972","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: 14