Learning shape correspondence with anisotropic convolutional neural networks

05/20/2016
by   Davide Boscaini, et al.
0

Establishing correspondence between shapes is a fundamental problem in geometry processing, arising in a wide variety of applications. The problem is especially difficult in the setting of non-isometric deformations, as well as in the presence of topological noise and missing parts, mainly due to the limited capability to model such deformations axiomatically. Several recent works showed that invariance to complex shape transformations can be learned from examples. In this paper, we introduce an intrinsic convolutional neural network architecture based on anisotropic diffusion kernels, which we term Anisotropic Convolutional Neural Network (ACNN). In our construction, we generalize convolutions to non-Euclidean domains by constructing a set of oriented anisotropic diffusion kernels, creating in this way a local intrinsic polar representation of the data (`patch'), which is then correlated with a filter. Several cascades of such filters, linear, and non-linear operators are stacked to form a deep neural network whose parameters are learned by minimizing a task-specific cost. We use ACNNs to effectively learn intrinsic dense correspondences between deformable shapes in very challenging settings, achieving state-of-the-art results on some of the most difficult recent correspondence benchmarks.

READ FULL TEXT

page 1

page 2

page 8

page 9

page 11

page 12

research
01/26/2015

Geodesic convolutional neural networks on Riemannian manifolds

Feature descriptors play a crucial role in a wide range of geometry anal...
research
01/29/2011

A correspondence-less approach to matching of deformable shapes

Finding a match between partially available deformable shapes is a chall...
research
06/16/2017

Dynamic Filters in Graph Convolutional Networks

Convolutional neural networks (CNNs) have massively impacted visual reco...
research
11/28/2018

Shared Representational Geometry Across Neural Networks

Different neural networks trained on the same dataset often learn simila...
research
10/23/2020

Unsupervised Dense Shape Correspondence using Heat Kernels

In this work, we propose an unsupervised method for learning dense corre...
research
09/18/2018

A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshes

The question of representation of 3D geometry is of vital importance whe...
research
12/06/2018

Self-supervised Learning of Dense Shape Correspondence

We introduce the first completely unsupervised correspondence learning a...

Please sign up or login with your details

Forgot password? Click here to reset