FlowTexNet: Fast Texture Synthesis for Massive Flow Field Visualization

Zijian Kang, Wenyao Zhang*, Na Wang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Flow field texture synthesis is a common and popular way to visualize flow fields. When massive flow fields are to be processed, existing algorithms based on line integral convolution (LIC) are not fast enough. In this paper, a new deep-learning-based method is proposed to synthesize flow textures for massive flow fields. Firstly, a deep neural network called FlowTexNet is built on the base of encoder-decoder architecture. Then the network is trained by flow textures generated by the original LIC algorithm. By this way, FlowTexNet can synthesize flow textures that have the same visualization effect as LIC textures. But FlowTexNet is much faster than the LIC algorithm. Test results show that the speedup of FlowTexNet is up to 450x when it is used to process massive flow fields and compared with the original LIC algorithm. Moreover, FlowTexNet can be applied to flow fields that are out of training, showing good generalization performance.

Original languageEnglish
Title of host publicationCACML 2023 - Conference Proceedings 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning
PublisherAssociation for Computing Machinery
Pages561-568
Number of pages8
ISBN (Electronic)9781450399449
DOIs
Publication statusPublished - 17 Mar 2023
Event2nd Asia Conference on Algorithms, Computing and Machine Learning, CACML 2023 - Shanghai, China
Duration: 17 Mar 202319 Mar 2023

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2nd Asia Conference on Algorithms, Computing and Machine Learning, CACML 2023
Country/TerritoryChina
CityShanghai
Period17/03/2319/03/23

Keywords

  • Deep learning
  • Flow field
  • Flow visualization
  • LIC
  • Texture synthesis

Fingerprint

Dive into the research topics of 'FlowTexNet: Fast Texture Synthesis for Massive Flow Field Visualization'. Together they form a unique fingerprint.

Cite this