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

by   Shunwang Gong, et al.
NYU college
Imperial College London

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.


page 4

page 6


SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels

We present Spline-based Convolutional Neural Networks (SplineCNNs), a va...

Shape-from-intrinsic operator

Shape-from-X is an important class of problems in the fields of geometry...

HeterSkinNet: A Heterogeneous Network for Skin Weights Prediction

Character rigging is universally needed in computer graphics but notorio...

Kernelized dense layers for facial expression recognition

Fully connected layer is an essential component of Convolutional Neural ...

3DN: 3D Deformation Network

Applications in virtual and augmented reality create a demand for rapid ...

HLO: Half-kernel Laplacian Operator for Surface Smoothing

This paper presents a simple yet effective method for feature-preserving...

Code Repositories


SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator (ICCV-W 2019)

view repo

Please sign up or login with your details

Forgot password? Click here to reset