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

Abstract

Intrinsic graph convolution operators with differentiable kernel functions play a crucial role in analyzing 3D shape meshes. In this paper, we present a fast and efficient intrinsic mesh convolution operator that does not rely on the intricate design of kernel function. We explicitly formulate the order of aggregating neighboring vertices, instead of learning weights between nodes, and then a fully connected layer follows to fuse local geometric structure information with vertex features. We provide extensive evidence showing that models based on this convolution operator are easier to train, and can efficiently learn invariant shape features. Specifically, we evaluate our method on three different types of tasks of dense shape correspondence, 3D facial expression classification, and 3D shape reconstruction, and show that it significantly outperforms state-of-the-art approaches while being significantly faster, without relying on shape descriptors. Our source code is available on GitHub.

The IEEE International Conference on Computer Vision (ICCV) Workshops, 2019

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric deep learning: going beyond Euclidean data
• How Powerful are Graph Neural Networks?
• Learning shape correspondence with anisotropic convolutional neural networks
• Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation
• Generating 3D faces using Convolutional Mesh Autoencoders
• A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshes