Meta Deformation Network: Meta Functionals for Shape Correspondence

06/26/2020
by   Daohan Lu, et al.
0

We present a new technique named "Meta Deformation Network" for 3D shape matching via deformation, in which a deep neural network maps a reference shape onto the parameters of a second neural network whose task is to give the correspondence between a learned template and query shape via deformation. We categorize the second neural network as a meta-function, or a function generated by another function, as its parameters are dynamically given by the first network on a per-input basis. This leads to a straightforward overall architecture and faster execution speeds, without loss in the quality of the deformation of the template. We show in our experiments that Meta Deformation Network leads to improvements on the MPI-FAUST Inter Challenge over designs that utilized a conventional decoder design that has non-dynamic parameters.

READ FULL TEXT
research
02/18/2021

DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates

We propose DeepMetaHandles, a 3D conditional generative model based on m...
research
08/26/2021

Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence

Shape correspondence from 3D deformation learning has attracted appealin...
research
08/17/2019

Deep Meta Functionals for Shape Representation

We present a new method for 3D shape reconstruction from a single image,...
research
01/08/2019

Selective metamorphosis for growth modelling with applications to landmarks

We present a framework for shape matching in computational anatomy allow...
research
09/30/2021

Identity-Disentangled Neural Deformation Model for Dynamic Meshes

Neural shape models can represent complex 3D shapes with a compact laten...
research
08/13/2019

Learning elementary structures for 3D shape generation and matching

We propose to represent shapes as the deformation and combination of lea...
research
11/20/2017

Stochastic metamorphosis with template uncertainties

In this paper, we investigate two stochastic perturbations of the metamo...

Please sign up or login with your details

Forgot password? Click here to reset