Hierarchical cloth simulation using deep neural networks

Young Jin Oh, Tae Min Lee, In Kwon Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (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 languageEnglish
Title of host publicationProceedings of Computer Graphics International, CGI 2018
PublisherAssociation for Computing Machinery
Pages139-146
Number of pages8
ISBN (Electronic)1595930361, 9781450364010
DOIs
Publication statusPublished - 2018 Jun 11
Event2018 Computer Graphics International Conference, CGI 2018 - Bintan, Indonesia
Duration: 2018 Jun 112018 Jun 14

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2018 Computer Graphics International Conference, CGI 2018
CountryIndonesia
CityBintan
Period18/6/1118/6/14

All Science Journal Classification (ASJC) codes

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

Fingerprint Dive into the research topics of 'Hierarchical cloth simulation using deep neural networks'. Together they form a unique fingerprint.

  • Cite this

    Oh, Y. J., Lee, T. M., & Lee, I. K. (2018). Hierarchical cloth simulation using deep neural networks. In Proceedings of Computer Graphics International, CGI 2018 (pp. 139-146). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3208159.3208162