P2P-NET: Bidirectional Point Displacement Net for Shape Transform
P2P-NET: Bidirectional Point Displacement Net for Shape Transform
复制标题
DOI：
10.1145/3197517.3201288
复制
发表时间：
2018-08-01
影响因子：
6.2
通讯作者：
Zhang, Hao
中科院分区：
文献类型：
--
作者：
Yin, Kangxue;Huang, Hui;Zhang, Hao
我们介绍了P2P-NET，这是一种通用的深度神经网络，它可以学习来自两个领域的基于点的形状表示之间的几何变换，例如，P2P-NET的架构是双向点位移网络的架构，其通过应用从数据学习的逐点位移向量将源点集转换为具有相同基数的目标点集的预测，反之亦然。P2P-NET是在来自源和目标域的成对形状上训练的，但不依赖于源和目标点集之间的点对点对应关系。训练损失结合了两个单向几何损失，每个损失在预测点集和目标点集之间强制执行形状相似性，以及交叉正则化项，以鼓励在相反方向上的位移向量之间的一致性。我们开发并提出了几个不同的应用程序，使我们的通用双向P2P-NET突出的有效性，多功能性和潜力，我们的网络在解决各种基于点的形状变换问题。
We introduce P2P-NET, a general-purpose deep neural network which learns geometric transformations between point-based shape representations from two domains, e.g., meso-skeletons and surfaces, partial and complete scans, etc. The architecture of the P2P-NET is that of a bi-directional point displacement network, which transforms a source point set to a prediction of the target point set with the same cardinality, and vice versa, by applying point-wise displacement vectors learned from data. P2P-NET is trained on paired shapes from the source and target domains, but without relying on point-to-point correspondences between the source and target point sets. The training loss combines two uni-directional geometric losses, each enforcing a shape-wise similarity between the predicted and the target point sets, and a cross-regularization term to encourage consistency between displacement vectors going in opposite directions. We develop and present several different applications enabled by our general-purpose bidirectional P2P-NET to highlight the effectiveness, versatility, and potential of our network in solving a variety of point-based shape transformation problems.