Exploring Physical Latent Spaces for High-Resolution Flow Restoration

Simple item page
dc.contributor.authorPaliard, Chloéen_US
dc.contributor.authorThuerey, Nilsen_US
dc.contributor.authorUm, Kiwonen_US
dc.contributor.editorGuthe, Michaelen_US
dc.contributor.editorGrosch, Thorstenen_US
dc.date.accessioned2023-09-25T11:40:23Z
dc.date.available2023-09-25T11:40:23Z
dc.date.issued2023
dc.description.abstractWe explore training deep neural network models in conjunction with physics simulations via partial differential equations (PDEs), using the simulated degrees of freedom as latent space for a neural network. In contrast to previous work, this paper treats the degrees of freedom of the simulated space purely as tools to be used by the neural network. We demonstrate this concept for learning reduced representations, as it is extremely challenging to faithfully preserve correct solutions over long time-spans with traditional reduced representations, particularly for solutions with large amounts of small scale features. This work focuses on the use of such physical, reduced latent space for the restoration of fine simulations, by training models that can modify the content of the reduced physical states as much as needed to best satisfy the learning objective. This autonomy allows the neural networks to discover alternate dynamics that significantly improve the performance in the given tasks. We demonstrate this concept for various fluid flows ranging from different turbulence scenarios to rising smoke plumes.en_US
dc.description.sectionheadersFluid Simulation and Visualization
dc.description.seriesinformationVision, Modeling, and Visualization
dc.identifier.doi10.2312/vmv.20231243
dc.identifier.isbn978-3-03868-232-5
dc.identifier.pages199-207
dc.identifier.pages9 pages
dc.identifier.urihttps://doi.org/10.2312/vmv.20231243
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vmv20231243
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Physical simulation; Learning latent representations
dc.subjectComputing methodologies → Physical simulation
dc.subjectLearning latent representations
dc.titleExploring Physical Latent Spaces for High-Resolution Flow Restorationen_US
Files
Original bundle
Now showing 1 - 3 of 3
No Thumbnail Available
Name:
199-207.pdf
Size:
33.92 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1010_mm.mp4
Size:
310.4 MB
Format:
Unknown data format
Download
No Thumbnail Available
Name:
paper1010_mm.pdf
Size:
21.03 MB
Format:
Adobe Portable Document Format
Download
Collections
VMV2023