Hierarchical cloth simulation using deep neural networks

Young Jin Oh; Tae Min Lee; In Kwon Lee

doi:10.1145/3208159.3208162

Hierarchical cloth simulation using deep neural networks

Young Jin Oh, Tae Min Lee, In Kwon Lee

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Citations (Scopus)

Abstract

Fast and reliable physically-based simulation techniques are essential for providing flexible visual effects for computer graphics content. In this paper, we propose a fast and reliable hierarchical cloth simulation method, which combines conventional physically-based simulation with deep neural networks (DNN). Simulations of the coarsest level of the hierarchical model are calculated using conventional physically-based simulations, and more detailed levels are generated by inference using DNN models. We demonstrate that our method generates reliable and fast cloth simulation results through experiments under various conditions.

Original language	English
Title of host publication	Proceedings of Computer Graphics International, CGI 2018
Publisher	Association for Computing Machinery
Pages	139-146
Number of pages	8
ISBN (Electronic)	1595930361, 9781450364010
DOIs	https://doi.org/10.1145/3208159.3208162
Publication status	Published - 2018 Jun 11
Event	2018 Computer Graphics International Conference, CGI 2018 - Bintan, Indonesia Duration: 2018 Jun 11 → 2018 Jun 14

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2018 Computer Graphics International Conference, CGI 2018
Country/Territory	Indonesia
City	Bintan
Period	18/6/11 → 18/6/14

Bibliographical note

Publisher Copyright:
© 2018 ACM.

All Science Journal Classification (ASJC) codes

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/3208159.3208162

Cite this

@inproceedings{ee3b9f7b76044bff9e79b6cf9b471a51,

title = "Hierarchical cloth simulation using deep neural networks",

abstract = "Fast and reliable physically-based simulation techniques are essential for providing flexible visual effects for computer graphics content. In this paper, we propose a fast and reliable hierarchical cloth simulation method, which combines conventional physically-based simulation with deep neural networks (DNN). Simulations of the coarsest level of the hierarchical model are calculated using conventional physically-based simulations, and more detailed levels are generated by inference using DNN models. We demonstrate that our method generates reliable and fast cloth simulation results through experiments under various conditions.",

author = "Oh, {Young Jin} and Lee, {Tae Min} and Lee, {In Kwon}",

note = "Publisher Copyright: {\textcopyright} 2018 ACM.; 2018 Computer Graphics International Conference, CGI 2018 ; Conference date: 11-06-2018 Through 14-06-2018",

year = "2018",

month = jun,

day = "11",

doi = "10.1145/3208159.3208162",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "139--146",

booktitle = "Proceedings of Computer Graphics International, CGI 2018",

}

Oh, YJ, Lee, TM & Lee, IK 2018, Hierarchical cloth simulation using deep neural networks. in Proceedings of Computer Graphics International, CGI 2018. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 139-146, 2018 Computer Graphics International Conference, CGI 2018, Bintan, Indonesia, 18/6/11. https://doi.org/10.1145/3208159.3208162

TY - GEN

T1 - Hierarchical cloth simulation using deep neural networks

AU - Oh, Young Jin

AU - Lee, Tae Min

AU - Lee, In Kwon

PY - 2018/6/11

Y1 - 2018/6/11

N2 - Fast and reliable physically-based simulation techniques are essential for providing flexible visual effects for computer graphics content. In this paper, we propose a fast and reliable hierarchical cloth simulation method, which combines conventional physically-based simulation with deep neural networks (DNN). Simulations of the coarsest level of the hierarchical model are calculated using conventional physically-based simulations, and more detailed levels are generated by inference using DNN models. We demonstrate that our method generates reliable and fast cloth simulation results through experiments under various conditions.

AB - Fast and reliable physically-based simulation techniques are essential for providing flexible visual effects for computer graphics content. In this paper, we propose a fast and reliable hierarchical cloth simulation method, which combines conventional physically-based simulation with deep neural networks (DNN). Simulations of the coarsest level of the hierarchical model are calculated using conventional physically-based simulations, and more detailed levels are generated by inference using DNN models. We demonstrate that our method generates reliable and fast cloth simulation results through experiments under various conditions.

UR - http://www.scopus.com/inward/record.url?scp=85062870738&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062870738&partnerID=8YFLogxK

U2 - 10.1145/3208159.3208162

DO - 10.1145/3208159.3208162

M3 - Conference contribution

AN - SCOPUS:85062870738

T3 - ACM International Conference Proceeding Series

SP - 139

EP - 146

BT - Proceedings of Computer Graphics International, CGI 2018

PB - Association for Computing Machinery

T2 - 2018 Computer Graphics International Conference, CGI 2018

Y2 - 11 June 2018 through 14 June 2018

ER -

Hierarchical cloth simulation using deep neural networks

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this