Geodesic convolutional neural networks on Riemannian manifolds

01/26/2015
by   Jonathan Masci, et al.
0

Feature descriptors play a crucial role in a wide range of geometry analysis and processing applications, including shape correspondence, retrieval, and segmentation. In this paper, we introduce Geodesic Convolutional Neural Networks (GCNN), a generalization of the convolutional networks (CNN) paradigm to non-Euclidean manifolds. Our construction is based on a local geodesic system of polar coordinates to extract "patches", which are then passed through a cascade of filters and linear and non-linear operators. The coefficients of the filters and linear combination weights are optimization variables that are learned to minimize a task-specific cost function. We use GCNN to learn invariant shape features, allowing to achieve state-of-the-art performance in problems such as shape description, retrieval, and correspondence.

READ FULL TEXT

Authors

page 7

05/20/2016

Learning shape correspondence with anisotropic convolutional neural networks

Establishing correspondence between shapes is a fundamental problem in g...
05/21/2018

Parallel Transport Convolution: A New Tool for Convolutional Neural Networks on Manifolds

Convolution has been playing a prominent role in various applications in...
06/16/2017

Dynamic Filters in Graph Convolutional Networks

Convolutional neural networks (CNNs) have massively impacted visual reco...
11/25/2016

Geometric deep learning on graphs and manifolds using mixture model CNNs

Deep learning has achieved a remarkable performance breakthrough in seve...
07/18/2017

Pruning Convolutional Neural Networks for Image Instance Retrieval

In this work, we focus on the problem of image instance retrieval with d...
03/13/2022

Euclidean Invariant Recognition of 2D Shapes Using Histograms of Magnitudes of Local Fourier-Mellin Descriptors

Because the magnitude of inner products with its basis functions are inv...
02/16/2021

Shape-Tailored Deep Neural Networks

We present Shape-Tailored Deep Neural Networks (ST-DNN). ST-DNN extend c...

Code Repositories

ShapeNet_data_preparation_toolbox

Scripts to prepare datasets for ShapeNet using the geodesic patch operator.


view repo

shape_pre_tool

shapenet_data_preparation_toolbox


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.