arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 1809.05910cs.LGcs.CVcs.GRstat.ML
收藏

MeshCNN:具有边缘的网络

MeshCNN: A Network with an Edge

Tel Aviv University(特拉维夫大学);Amazon(亚马逊)

Rana Hanocka, Amir Hertz, Noa Fish, Raja Giryes, Shachar Fleishman, Daniel Cohen-Or

摘要:

多边形网格为3D形状提供了有效的表示。它们明确地捕获形状表面和拓扑结构,并利用非均匀性来表示大的平坦区域以及尖锐,复杂的特征。然而,这种不均匀性和不规则性抑制了使用结合卷积和池化操作的神经网络的网格分析工作。在本文中,我们利用网格的独特属性,使用MeshCNN直接分析3D形状,MeshCNN是一种专门为三角形网格设计的卷积神经网络。类似于经典的CNN,MeshCNN通过利用其内在的测地线连接,结合了在网格边缘上操作的专用卷积和池化层。卷积应用于边和它们的入射三角形的四个边,并且池化通过保留表面拓扑的边折叠操作来应用,从而为后续卷积生成新的网格连接。MeshCNN学习哪些边要折叠,从而形成一个任务驱动的过程,在这个过程中,网络暴露和扩展重要的特征,同时丢弃冗余的特征。我们证明了我们的任务驱动的池应用于3D网格的各种学习任务的有效性。

英文摘要:

Polygonal meshes provide an efficient representation for 3D shapes. They explicitly capture both shape surface and topology, and leverage non-uniformity to represent large flat regions as well as sharp, intricate features. This non-uniformity and irregularity, however, inhibits mesh analysis efforts using neural networks that combine convolution and pooling operations. In this paper, we utilize the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes. Analogous to classic CNNs, MeshCNN combines specialized convolution and pooling layers that operate on the mesh edges, by leveraging their intrinsic geodesic connections. Convolutions are applied on edges and the four edges of their incident triangles, and pooling is applied via an edge collapse operation that retains surface topology, thereby, generating new mesh connectivity for the subsequent convolutions. MeshCNN learns which edges to collapse, thus forming a task-driven process where the network exposes and expands the important features while discarding the redundant ones. We demonstrate the effectiveness of our task-driven pooling on various learning tasks applied to 3D meshes.

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。

↑