Convolutional networks have been extremely successful for regular data structures such as 2D images and 3D voxel grids. The transposition to meshes is, however, not straight-forward due to their irregular structure. We explore how the dual, face-based representation of triangular meshes can be leveraged as a data structure for graph convolutional networks. In the dual mesh, each node (face) has a fixed number of neighbors, which makes the networks less susceptible to overfitting on the mesh topology, and also al-lows the use of input features that are naturally defined over faces, such as surface normals and face areas. We evaluate the dual approach on the shape correspondence task on theFaust human shape dataset and variants of it with differ-ent mesh topologies. Our experiments show that results of graph convolutional networks improve when defined over the dual rather than primal mesh. Moreover, our models that explicitly leverage the neighborhood regularity of dual meshes allow improving results further while being more robust to changes in the mesh topology.
翻译:对于像 2D 图像和 3D voxel 网格这样的常规数据结构来说, 革命网络非常成功。 但是, 向 meshes 的转换并不是直接向前的, 因为它们的结构不正常 。 我们探索如何将三角环形的双面表示作为图形相形网络的数据结构。 在双面网格中, 每个节点( 脸) 都有固定的邻居数, 这使得这些网络更不易在网目表层上过度适应, 也降低了对面自然定义的输入特性的使用, 如表面常态和面部。 我们评估了Faust 人类形状数据集形状对应任务的双向方法, 以及其变式与不同网状结构。 我们的实验显示, 图形相形网络的结果在以双面而非原始网格定义时会得到改善。 此外, 我们的模型明确利用了双面网点的周围规律性, 可以进一步改进结果, 同时更有力地改变网格表。