Splash in a Flash: Sharpness-aware Minimization for Efficient Liquid Splash Simulation

dc.contributor.authorJetly, Vishruten_US
dc.contributor.authorIbayashi, Hikaruen_US
dc.contributor.authorNakano, Aiichiroen_US
dc.contributor.editorSauvage, Basileen_US
dc.contributor.editorHasic-Telalovic, Jasminkaen_US
dc.date.accessioned2022-04-22T07:54:23Z
dc.date.available2022-04-22T07:54:23Z
dc.date.issued2022
dc.description.abstractWe present sharpness-aware minimization (SAM) for fluid dynamics which can efficiently learn the plausible dynamics of liquid splashes. Due to its ability to achieve robust and generalizing solutions, SAM efficiently converges to a parameter set that predicts plausible dynamics of elusive liquid splashes. Our training scheme requires 6 times smaller number of epochs to converge and, 4 times shorter wall-clock time. Our result shows that sharpness of loss function has a close connection to the plausibility of fluid dynamics and suggests further applicability of SAM to machine learning based fluid simulation.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationEurographics 2022 - Posters
dc.identifier.doi10.2312/egp.20221003
dc.identifier.isbn978-3-03868-171-7
dc.identifier.issn1017-4656
dc.identifier.pages7-9
dc.identifier.pages3 pages
dc.identifier.urihttps://doi.org/10.2312/egp.20221003
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/egp20221003
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Animation --> Fluid simulation; Methods and Applications --> Machine Learning; Neural Nets ; Optimization; Visualization --> Scientific Visualization
dc.subjectAnimation
dc.subjectFluid simulation
dc.subjectMethods and Applications
dc.subjectMachine Learning
dc.subjectNeural Nets
dc.subjectOptimization
dc.subjectVisualization
dc.subjectScientific Visualization
dc.titleSplash in a Flash: Sharpness-aware Minimization for Efficient Liquid Splash Simulationen_US
Files
Original bundle
Now showing 1 - 3 of 3
Loading...
Thumbnail Image
Name:
007-009.pdf
Size:
3.05 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
poster1003_poster_pdf.pdf
Size:
1.5 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
poster1003_video.mp4
Size:
434.01 MB
Format:
Unknown data format