Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches. While CNNs naturally extend to other domains, such as audio and video, where data is also organized in rectangular grids, they do not easily generalize to other types of data such as 3D shape meshes, social network graphs or molecular graphs. To handle such data, we propose a novel graph-convolutional network architecture that builds on a generic formulation that relaxes the 1-to-1 correspondence between filter weights and data elements around the center of the convolution. The main novelty of our architecture is that the shape of the filter is a function of the features in the previous network layer, which is learned as an integral part of the neural network. Experimental evaluations on digit recognition, semi-supervised document classification, and 3D shape correspondence yield state-of-the-art results, significantly improving over previous work for shape correspondence.

该研究提出了一种新颖的图卷积算子，通过动态地计算网络所学习到的特征与图上邻域之间的对应关系来实现任意连接的图邻域与滤波器权重之间的对应关系，并通过实验结果验证该方法可以从原始输入坐标学习有效的形状表示，而不依赖于形状描述符。

FeaStNet: 基于特征导向的图卷积用于三维形状分析