A Neural-Network-Based Approach for Loose-Fitting Clothing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jin, Yongxu, Omens, Dalton, Geng, Zhenglin, Teran, Joseph, Kumar, Abishek, Tashiro, Kenji, Fedkiw, Ronald
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911854021836800
author Jin, Yongxu
Omens, Dalton
Geng, Zhenglin
Teran, Joseph
Kumar, Abishek
Tashiro, Kenji
Fedkiw, Ronald
author_facet Jin, Yongxu
Omens, Dalton
Geng, Zhenglin
Teran, Joseph
Kumar, Abishek
Tashiro, Kenji
Fedkiw, Ronald
contents Since loose-fitting clothing contains dynamic modes that have proven to be difficult to predict via neural networks, we first illustrate how to coarsely approximate these modes with a real-time numerical algorithm specifically designed to mimic the most important ballistic features of a classical numerical simulation. Although there is some flexibility in the choice of the numerical algorithm used as a proxy for full simulation, it is essential that the stability and accuracy be independent from any time step restriction or similar requirements in order to facilitate real-time performance. In order to reduce the number of degrees of freedom that require approximations to their dynamics, we simulate rigid frames and use skinning to reconstruct a rough approximation to a desirable mesh; as one might expect, neural-network-based skinning seems to perform better than linear blend skinning in this scenario. Improved high frequency deformations are subsequently added to the skinned mesh via a quasistatic neural network (QNN). In contrast to recurrent neural networks that require a plethora of training data in order to adequately generalize to new examples, QNNs perform well with significantly less training data.
format Preprint
id arxiv_https___arxiv_org_abs_2404_16896
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Neural-Network-Based Approach for Loose-Fitting Clothing
Jin, Yongxu
Omens, Dalton
Geng, Zhenglin
Teran, Joseph
Kumar, Abishek
Tashiro, Kenji
Fedkiw, Ronald
Graphics
Machine Learning
Since loose-fitting clothing contains dynamic modes that have proven to be difficult to predict via neural networks, we first illustrate how to coarsely approximate these modes with a real-time numerical algorithm specifically designed to mimic the most important ballistic features of a classical numerical simulation. Although there is some flexibility in the choice of the numerical algorithm used as a proxy for full simulation, it is essential that the stability and accuracy be independent from any time step restriction or similar requirements in order to facilitate real-time performance. In order to reduce the number of degrees of freedom that require approximations to their dynamics, we simulate rigid frames and use skinning to reconstruct a rough approximation to a desirable mesh; as one might expect, neural-network-based skinning seems to perform better than linear blend skinning in this scenario. Improved high frequency deformations are subsequently added to the skinned mesh via a quasistatic neural network (QNN). In contrast to recurrent neural networks that require a plethora of training data in order to adequately generalize to new examples, QNNs perform well with significantly less training data.
title A Neural-Network-Based Approach for Loose-Fitting Clothing
topic Graphics
Machine Learning
url https://arxiv.org/abs/2404.16896