论文标题
从3D点云中学习零件边界
Learning Part Boundaries from 3D Point Clouds
论文作者
论文摘要
我们提出了一种检测以3D形状为点云的零件边界的方法。我们的方法基于图形卷积网络体系结构，该结构输出了一个点位于以3D形状分离两个或多个零件的区域中的概率。我们的边界检测器非常通用：可以训练它以定位3D建模中常用的语义零件或几何原语的边界。我们的实验表明，与替代方案相比，我们的方法可以提取更准确的边界。我们还展示了网络在细粒的语义形状细分中的应用，在零件标记性能方面，我们还显示出改进。
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.
