Mesh-based Autoencoders for Localized Deformation Component Analysis

09/13/2017
by   Qingyang Tan, et al.
0

Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing. Several methods have recently been developed, with an aim to extract intuitive and interpretable deformation components. However, these techniques suffer from fundamental limitations especially for meshes with noise or large-scale deformations, and may not always be able to identify important deformation components. In this paper we propose a novel mesh-based autoencoder architecture that is able to cope with meshes with irregular topology. We introduce sparse regularization in this framework, which along with convolutional operations, helps localize deformations. Our framework is capable of extracting localized deformation components from mesh data sets with large-scale deformations and is robust to noise. It also provides a nonlinear approach to reconstruction of meshes using the extracted basis, which is more effective than the current linear combination approach. Extensive experiments show that our method outperforms state-of-the-art methods in both qualitative and quantitative evaluations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/04/2020

Multiscale Mesh Deformation Component Analysis with Attention-based Autoencoders

Deformation component analysis is a fundamental problem in geometry proc...
research
09/05/2017

Sparse Data Driven Mesh Deformation

Example-based mesh deformation methods are powerful tools for realistic ...
research
07/23/2018

Robust Edge-Preserved Surface Mesh Polycube Deformation

The problem of polycube construction or deformation is an essential prob...
research
03/10/2020

A Compact Spectral Descriptor for Shape Deformations

Modern product design in the engineering domain is increasingly driven b...
research
06/08/2020

Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels

Learning latent representations of registered meshes is useful for many ...
research
05/31/2021

Learning Free-Form Deformation for 3D Face Reconstruction from In-The-Wild Images

The 3D Morphable Model (3DMM), which is a Principal Component Analysis (...
research
02/23/2021

Deep Deformation Detail Synthesis for Thin Shell Models

In physics-based cloth animation, rich folds and detailed wrinkles are a...

Please sign up or login with your details

Forgot password? Click here to reset