arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2007.07563cs.CVcs.CG
收藏

从三维点云数据学习零件边界

Learning Part Boundaries from 3D Point Clouds

University of Cyprus(塞浦路斯大学);RISE CoE(RISE卓越中心);University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Marios Loizou, Melinos Averkiou, Evangelos Kalogerakis

摘要:

我们提出了一种方法,检测表示为点云的3D形状的零件的边界。我们的方法是基于一个图卷积网络架构,输出一个点的概率位于一个区域,在一个3D形状分开两个或多个部分。我们的边界检测器是相当通用的:它可以被训练来定位3D建模中常用的语义部分或几何图元的边界。我们的实验表明,我们的方法可以提取更准确的边界,更接近地面实况的替代品相比。我们还展示了我们的网络在细粒度语义形状分割中的应用,其中我们还展示了部分标记性能的改进。

英文摘要:

We present a method that detects boundaries of parts in 3D shapes represented as point clouds. Our method is based on a graph convolutional network architecture that outputs a probability for a point to lie in an area that separates two or more parts in a 3D shape. Our boundary detector is quite generic: it can be trained to localize boundaries of semantic parts or geometric primitives commonly used in 3D modeling. Our experiments demonstrate that our method can extract more accurate boundaries that are closer to ground-truth ones compared to alternatives. We also demonstrate an application of our network to fine-grained semantic shape segmentation, where we also show improvements in terms of part labeling performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑