Mesh Convolutional Networks with Face and Vertex Feature Operators
Mesh Convolutional Networks with Face and Vertex Feature Operators
复制标题
具有面和顶点特征算子的网状卷积网络
DOI：
--
复制
发表时间：
2016
影响因子：
5.2
通讯作者：
Anil K. Jain
中科院分区：
文献类型：
--
作者：
Kai Cao;Dinh;Cori Tymoszek;Anil K. Jain
深度学习技术已被证明在许多应用中有效，但是这些实现主要适用于一个或两个维度的数据。由于其不规则性和复杂性，处理3D数据更具挑战性，并且对将深度学习技术调整到3D领域的兴趣越来越大。最近的一种称为Meshcnn的成功方法由应用于三角形网格边缘的一组卷积和合并操作员组成。尽管这种方法产生了出色的3D形状的分类和分割，但它只能应用于网格的边缘，这可能构成焦点是网格其他原始物的应用。在这项研究中，我们建议基于面部和基于顶点的网络卷积网络的操作员。我们基于MeshCNN网络设计了两个新颖的体系结构，分别可以在网格的面部和顶点上操作。我们证明，所提出的基于面部的体系结构的表现优于网格分类和网格细分中的原始MESHCNN实现，在基准数据集上设置了新的最新技术。此外，我们将基于顶点的操作员扩展到适合Point2Mesh模型中，以从清洁，嘈杂和不完整的点云中进行网格重建。尽管没有观察到统计学上显着的性能提高，但与原始的Point2MESH模型相比，建议的方法分别减少了91％和20％。
Deep learning techniques have proven effective in many applications, but these implementations mostly apply to data in one or two dimensions. Handling 3D data is more challenging due to its irregularity and complexity, and there is a growing interest in adapting deep learning techniques to the 3D domain. A recent successful approach called MeshCNN consists of a set of convolutional and pooling operators applied to the edges of triangular meshes. While this approach produced superb results in classification and segmentation of 3D shapes, it can only be applied to edges of a mesh, which can constitute a disadvantage for applications where the focuses are other primitives of the mesh. In this study, we propose face-based and vertex-based operators for mesh convolutional networks. We design two novel architectures based on the MeshCNN network that can operate on faces and vertices of a mesh, respectively. We demonstrate that the proposed face-based architecture outperforms the original MeshCNN implementation in mesh classification and mesh segmentation, setting the new state of the art on benchmark datasets. In addition, we extend the vertex-based operator to fit in the Point2Mesh model for mesh reconstruction from clean, noisy, and incomplete point clouds. While no statistically significant performance improvements are observed, the model training and inference time are reduced by the proposed approach by 91% and 20%, respectively, as compared with the original Point2Mesh model.