Log In Sign Up

Shape correspondences from learnt template-based parametrization

by   Thibault Groueix, et al.

We present a new deep learning approach for matching deformable shapes by using a model which jointly encodes 3D shapes and correspondences. This is achieved by factoring the surface representation into (i) a template, that parameterizes the surface, and (ii) a learnt feature vector that parameterizes the function which transforms the template into the input surface. We show that our network can directly predict the feature vector and thus correspondences for a new input shape, but also that correspondence quality can be significantly improved by an additional regression step. This additional step improves the shape feature vector by minimizing the Chamfer distance between the input and parameterized shape. We show that this produces both a better shape representation and better correspondences. We demonstrate that our simple approach improves state of the art results on the difficult FAUST inter challenge, with an average correspondence error of 2.88cm. We also show results on the real scans from the SCAPE dataset and the synthetically perturbed shapes from the TOSCA dataset, including non-human shapes.


page 14

page 20


Unsupervised cycle-consistent deformation for shape matching

We propose a self-supervised approach to deep surface deformation. Given...

On Nonrigid Shape Similarity and Correspondence

An important operation in geometry processing is finding the corresponde...

High-Resolution Augmentation for Automatic Template-Based Matching of Human Models

We propose a new approach for 3D shape matching of deformable human shap...

Compact Part-Based Shape Spaces for Dense Correspondences

We consider the problem of establishing dense correspondences within a s...

Learning elementary structures for 3D shape generation and matching

We propose to represent shapes as the deformation and combination of lea...

Template-based Monocular 3D Shape Recovery using Laplacian Meshes

We show that by extending the Laplacian formalism, which was first intro...

Super Compaction and Pluripotent Shape Transformation via Algorithmic Stacking for 3D Deployable Structures

Origami structures enabled by folding and unfolding can create complex 3...