Neural UpFlow: A Scene Flow Learning Approach to Increase the Apparent Resolution of Particle-Based Liquids

Simple item page
dc.contributor.authorRoy, Brunoen_US
dc.contributor.authorPoulin, Pierreen_US
dc.contributor.authorPaquette, Ericen_US
dc.contributor.editorNarain, Rahul and Neff, Michael and Zordan, Victoren_US
dc.date.accessioned2022-02-07T13:32:36Z
dc.date.available2022-02-07T13:32:36Z
dc.date.issued2021
dc.description.abstractWe present a novel up-resing technique for generating high-resolution liquids based on scene flow estimation using deep neural networks. Our approach infers and synthesizes small- and large-scale details solely from a low-resolution particle-based liquid simulation. The proposed network leverages neighborhood contributions to encode inherent liquid properties throughout convolutions. We also propose a particle-based approach to interpolate between liquids generated from varying simulation discretizations using a state-of-the-art bidirectional optical flow solver method for fluids in addition with a novel key-event topological alignment constraint. In conjunction with the neighborhood contributions, our loss formulation allows the inference model throughout epochs to reward important differences in regard to significant gaps in simulation discretizations. Even when applied in an untested simulation setup, our approach is able to generate plausible high-resolution details. Using this interpolation approach and the predicted displacements, our approach combines the input liquid properties with the predicted motion to infer semi-Lagrangian advection. We furthermore showcase how the proposed interpolation approach can facilitate generating large simulation datasets with a subset of initial condition parameters.en_US
dc.description.number3
dc.description.sectionheaderspapers
dc.description.seriesinformationProceedings of the ACM on Computer Graphics and Interactive Techniques
dc.description.volume4
dc.identifier.doi10.1145/3480147
dc.identifier.issn2577-6193
dc.identifier.urihttps://doi.org/10.1145/3480147
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1145/3480147
dc.publisherACMen_US
dc.subjectComputing methodologies
dc.subjectPhysical simulation
dc.subjectfluid simulation
dc.subjectparticle
dc.subjectbased liquid
dc.subjectdeformation field
dc.subjectoptical flow
dc.subjectup
dc.subjectresing
dc.subjectmachine learning
dc.subjectdeep neural network
dc.titleNeural UpFlow: A Scene Flow Learning Approach to Increase the Apparent Resolution of Particle-Based Liquidsen_US
Files
Collections
SCA 2021: Eurographics/SIGGRAPH Symposium on Computer Animation