FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis

Abstract

Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches. CNNs do not easily extend, however, to data that are not represented by regular grids, such as 3D shape meshes or other graphstructured data, to which traditional local convolution operators do not directly apply. To address this problem, we propose a novel graph-convolution operator to establish correspondences between filter weights and graph neighborhoods with arbitrary connectivity. The key novelty of our approach is that these correspondences are dynamically computed from features learned by the network, rather than relying on predefined static coordinates over the graph as in previous work. We obtain excellent experimental results that significantly improve over previous state-of-theart shape correspondence results. This shows that our approach can learn effective shape representations from raw input coordinates, without relying on shape descriptors.

SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator

“…In this section, we evaluate our method on three tasks, i.e., dense shape correspondence, 3D facial expression classification, and 3D shape reconstruction. We compare our method against FeaStNet [34], MoNet [28], ChebyNet [13] and SpiralNet [25]. To enable a fair comparison, the model architectures and the kernel size of different convolutions…”

“…Monti et al [28] established a unified framework generalizing CNN architectures to noneuclidean domains. Verma et al [34] proposed a graphconvolution operator of dynamic correspondence between filter weights and neighboring nodes with arbitrary connectivity, which is computed from features learned by the network. Lim et al [25] firstly proposed SpiralNet and applied it on this task, which achieved highly competitive results.…”

“…In contrast to previous approaches [14,28,34] which aggregate neighboring node features based on trainable weight functions, our method encodes node features under a explicitly defined spiral sequence, and a fully connected layer follows to encode input features combined with ordering information. It is a simple yet efficient approach.…”

“…We validate our method on a collection of threedimensional meshes solving the task of shape correspondence similar to [6,27,28,34]. Shape correspondence refers to the task of labeling each node of a given shape to the corresponding node of a reference shape [27].…”

Graph-Based Method for Anomaly Detection in Functional Brain Network using Variational Autoencoder

“…In spite of individual alteration, human brains performed common patterns among different subjects. Therefore, algorithms base on graph are essential tool to capture and model complicated relationship between functional connectivity.in this work, we used a model of graph embedding to convert graph data into a low dimensional and compaction continuous feature space that is able to detect abnormal parts of input graphs [17] which is involved with graph matching and partial graph completion problems. To develop this algorithms need to present a generative model that construct from a Graph Varational Autoencoder with hypersphere distribution [18,19,20].…”