DeepAI
Log In Sign Up

Multiscale Mesh Deformation Component Analysis with Attention-based Autoencoders

12/04/2020
by   Jie Yang, et al.
5

Deformation component analysis is a fundamental problem in geometry processing and shape understanding. Existing approaches mainly extract deformation components in local regions at a similar scale while deformations of real-world objects are usually distributed in a multi-scale manner. In this paper, we propose a novel method to exact multiscale deformation components automatically with a stacked attention-based autoencoder. The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions, and the stacked attention-based autoencoder is learned to represent the deformation components at different scales. Quantitative and qualitative evaluations show that our method outperforms state-of-the-art methods. Furthermore, with the multiscale deformation components extracted by our method, the user can edit shapes in a coarse-to-fine fashion which facilitates effective modeling of new shapes.

READ FULL TEXT

page 3

page 6

page 10

page 11

page 12

page 13

09/13/2017

Mesh-based Autoencoders for Localized Deformation Component Analysis

Spatially localized deformation components are very useful for shape ana...
03/24/2018

AAANE: Attention-based Adversarial Autoencoder for Multi-scale Network Embedding

Network embedding represents nodes in a continuous vector space and pres...
10/11/2022

Neural Shape Deformation Priors

We present Neural Shape Deformation Priors, a novel method for shape man...
06/27/2018

Divergence-Free Shape Interpolation and Correspondence

We present a novel method to model and calculate deformation fields betw...
01/19/2021

Joint Learning of 3D Shape Retrieval and Deformation

We propose a novel technique for producing high-quality 3D models that m...
09/06/2019

Real-time Deformation with Coupled Cages and Skeletons

Skeleton-based and cage-based deformation techniques represent the two m...