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 graph-structured 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-the-art shape correspondence results. This shows that our approach can learn effective shape representations from raw input coordinates, without relying on shape descriptors.

References in corpus (3)

• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Deep Convolutional Networks on Graph-Structured Data
• Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Space

Cited by in corpus (8)

• PAN: Path Integral Based Convolution for Deep Graph Neural Networks
• Unsupervised Learning of 3D Point Set Registration
• Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling
• Variational Autoencoders for Deforming 3D Mesh Models
• Unsupervised Learning of Global Registration of Temporal Sequence of Point Clouds
• Geometrically Principled Connections in Graph Neural Networks
• Multi-scale Receptive Fields Graph Attention Network for Point Cloud Classification
• Surrogate Modelling for Injection Molding Processes using Machine Learning