Frequency-Aware Reconstruction of Fluid Simulations with Generative Networks

Simple item page
dc.contributor.authorBiland, Simonen_US
dc.contributor.authorAzevedo, Vinicius C.en_US
dc.contributor.authorKim, Byungsooen_US
dc.contributor.authorSolenthaler, Barbaraen_US
dc.contributor.editorWilkie, Alexander and Banterle, Francescoen_US
dc.date.accessioned2020-05-24T13:43:04Z
dc.date.available2020-05-24T13:43:04Z
dc.date.issued2020
dc.description.abstractConvolutional neural networks were recently employed to fully reconstruct fluid simulation data from a set of reduced parameters. However, since (de-)convolutions traditionally trained with supervised l1-loss functions do not discriminate between low and high frequencies in the data, the error is not minimized efficiently for higher bands. This directly correlates with the quality of the perceived results, since missing high frequency details are easily noticeable. In this paper, we analyze the reconstruction quality of generative networks and present a frequency-aware loss function that is able to focus on specific bands of the dataset during training time. We show that our approach improves reconstruction quality of fluid simulation data in mid-frequency bands, yielding perceptually better results while requiring comparable training time.en_US
dc.description.sectionheadersModelling - Simulation - Visualisation
dc.description.seriesinformationEurographics 2020 - Short Papers
dc.identifier.doi10.2312/egs.20201019
dc.identifier.isbn978-3-03868-101-4
dc.identifier.issn1017-4656
dc.identifier.pages65-68
dc.identifier.urihttps://doi.org/10.2312/egs.20201019
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/egs20201019
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/]
dc.subjectComputing methodologies
dc.subjectPhysical simulation
dc.subjectNeural networks
dc.titleFrequency-Aware Reconstruction of Fluid Simulations with Generative Networksen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
065-068.pdf
Size:
3.42 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2020 - Short Papers