MGCN: Descriptor Learning using Multiscale GCNs

by   Yiqun Wang, et al.

We propose a novel framework for computing descriptors for characterizing points on three-dimensional surfaces. First, we present a new non-learned feature that uses graph wavelets to decompose the Dirichlet energy on a surface. We call this new feature wavelet energy decomposition signature (WEDS). Second, we propose a new multiscale graph convolutional network (MGCN) to transform a non-learned feature to a more discriminative descriptor. Our results show that the new descriptor WEDS is more discriminative than the current state-of-the-art non-learned descriptors and that the combination of WEDS and MGCN is better than the state-of-the-art learned descriptors. An important design criterion for our descriptor is the robustness to different surface discretizations including triangulations with varying numbers of vertices. Our results demonstrate that previous graph convolutional networks significantly overfit to a particular resolution or even a particular triangulation, but MGCN generalizes well to different surface discretizations. In addition, MGCN is compatible with previous descriptors and it can also be used to improve the performance of other descriptors, such as the heat kernel signature, the wave kernel signature, or the local point signature.


page 7

page 8

page 11


Global spectral graph wavelet signature for surface analysis of carpal bones

In this paper, we present a spectral graph wavelet approach for shape an...

Signature of Geometric Centroids for 3D Local Shape Description and Partial Shape Matching

Depth scans acquired from different views may contain nuisances such as ...

Learning a Local Feature Descriptor for 3D LiDAR Scans

Robust data association is necessary for virtually every SLAM system and...

Signature Recognition using Multi Scale Fourier Descriptor And Wavelet Transform

This paper present a novel off-line signature recognition method based o...

Multiscale Fractal Descriptors Applied to Nanoscale Images

This work proposes the application of fractal descriptors to the analysi...

Spectral descriptors for deformable shapes

Informative and discriminative feature descriptors play a fundamental ro...

Thesis: Multiple Kernel Learning for Object Categorization

Object Categorization is a challenging problem, especially when the imag...

Code Repositories


MGCN: Descriptor Learning using Multiscale GCNs (SIGGRAPH 2020)

view repo