Estimating Cloth Simulation Parameters From a Static Drape Using Neural Networks

We present a neural network learning approach for estimating a set of cloth simulation parameters from a static drape of a given fabric. We use a variant of Cusick's drape, which is used in the fashion textile industry to classify fabric according to mechanical properties. In order to produce a...

Full description

Bibliographic Details
Main Authors: Eunjung Ju, Myung Geol Choi
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9239275/
_version_ 1818917753246973952
author Eunjung Ju
Myung Geol Choi
author_facet Eunjung Ju
Myung Geol Choi
author_sort Eunjung Ju
collection DOAJ
description We present a neural network learning approach for estimating a set of cloth simulation parameters from a static drape of a given fabric. We use a variant of Cusick's drape, which is used in the fashion textile industry to classify fabric according to mechanical properties. In order to produce a large enough set of reliable training data, we first randomly sample simulation parameters using a Gaussian mixture model that is fitted with 400 sets of primary simulation parameters derived from real fabrics. Then, we simulate our modified Cusick's drape for each sample parameter set. To learn the training data, we propose a two-stream fully connected neural network model. We prove the suitability of our neural network model through comparisons of the learning errors and accuracy with other similar neural network and linear regression models. Additionally, to demonstrate the practicality of our method, we reproduce the drape shapes of real fabrics using the simulation parameters estimated from the trained neural networks.
first_indexed 2024-12-20T00:39:04Z
format Article
id doaj.art-848cf7a281f74ea7948291ea21b69af8
institution Directory Open Access Journal
issn 2169-3536
language English
last_indexed 2024-12-20T00:39:04Z
publishDate 2020-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj.art-848cf7a281f74ea7948291ea21b69af82022-12-21T19:59:41ZengIEEEIEEE Access2169-35362020-01-01819511319512110.1109/ACCESS.2020.30337659239275Estimating Cloth Simulation Parameters From a Static Drape Using Neural NetworksEunjung Ju0https://orcid.org/0000-0002-4549-9277Myung Geol Choi1https://orcid.org/0000-0002-6089-9455CLO Virtual Fashion Inc., Seoul, South KoreaDigital Media Department, The Catholic University of Korea, Bucheon, South KoreaWe present a neural network learning approach for estimating a set of cloth simulation parameters from a static drape of a given fabric. We use a variant of Cusick's drape, which is used in the fashion textile industry to classify fabric according to mechanical properties. In order to produce a large enough set of reliable training data, we first randomly sample simulation parameters using a Gaussian mixture model that is fitted with 400 sets of primary simulation parameters derived from real fabrics. Then, we simulate our modified Cusick's drape for each sample parameter set. To learn the training data, we propose a two-stream fully connected neural network model. We prove the suitability of our neural network model through comparisons of the learning errors and accuracy with other similar neural network and linear regression models. Additionally, to demonstrate the practicality of our method, we reproduce the drape shapes of real fabrics using the simulation parameters estimated from the trained neural networks.https://ieeexplore.ieee.org/document/9239275/Fabricscomputer simulationparameter estimationartificial neural networksCusick’s drape
spellingShingle Eunjung Ju
Myung Geol Choi
Estimating Cloth Simulation Parameters From a Static Drape Using Neural Networks
IEEE Access
Fabrics
computer simulation
parameter estimation
artificial neural networks
Cusick’s drape
title Estimating Cloth Simulation Parameters From a Static Drape Using Neural Networks
title_full Estimating Cloth Simulation Parameters From a Static Drape Using Neural Networks
title_fullStr Estimating Cloth Simulation Parameters From a Static Drape Using Neural Networks
title_full_unstemmed Estimating Cloth Simulation Parameters From a Static Drape Using Neural Networks
title_short Estimating Cloth Simulation Parameters From a Static Drape Using Neural Networks
title_sort estimating cloth simulation parameters from a static drape using neural networks
topic Fabrics
computer simulation
parameter estimation
artificial neural networks
Cusick’s drape
url https://ieeexplore.ieee.org/document/9239275/
work_keys_str_mv AT eunjungju estimatingclothsimulationparametersfromastaticdrapeusingneuralnetworks
AT myunggeolchoi estimatingclothsimulationparametersfromastaticdrapeusingneuralnetworks