GaussFluids: Reconstructing Lagrangian Fluid Particles from Videos via Gaussian Splatting

Simple item page
dc.contributor.authorDu, Feilongen_US
dc.contributor.authorZhang, Yalanen_US
dc.contributor.authorJi, Yihangen_US
dc.contributor.authorWang, Xiaokunen_US
dc.contributor.authorYao, Chaoen_US
dc.contributor.authorKosinka, Jirien_US
dc.contributor.authorFrey, Steffenen_US
dc.contributor.authorTelea, Alexandruen_US
dc.contributor.authorBan, Xiaojuanen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorHan, Ping-Hsuanen_US
dc.contributor.editorLin, Shih-Syunen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorSchneider, Teseoen_US
dc.contributor.editorTsai, Hsin-Rueyen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.contributor.editorZhang, Eugeneen_US
dc.date.accessioned2025-10-07T06:04:07Z
dc.date.available2025-10-07T06:04:07Z
dc.date.issued2025
dc.description.abstractFluid simulation typically depends on manual modeling and visual assessment to achieve desired outcomes, which lacks objectivity and efficiency. To address this limitation, we propose GaussFluids, a novel approach for directly reconstructing temporally and spatially continuous Lagrangian fluid particles from videos. We employ a Lagrangian particle-based method instead of an Eulerian grid as it provides a direct spatial mass representation and is more suitable for capturing fine fluid details. First, to make discrete fluid particles differentiable over time and space, we extend Lagrangian particles with Gaussian probability densities, termed Gaussian Particles, constructing a differentiable fluid particle renderer that enables direct optimization of particle positions from visual data. Second, we introduce a fixed-length transform feature for each Gaussian Particle to encode pose changes over continuous time. Next, to preserve fundamental fluid physics-particularly incompressibility-we incorporate a density-based soft constraint to guide particle distribution within the fluid. Furthermore, we propose a hybrid loss function that focuses on maintaining visual, physical, and geometric consistency, along with an improved density optimization module to efficiently reconstruct spatiotemporally continuous fluids. We demonstrate the effectiveness of GaussFluids on multiple synthetic and real-world datasets, showing its capability to accurately reconstruct temporally and spatially continuous, physically plausible Lagrangian fluid particles from videos. Additionally, we introduce several downstream tasks, including novel view synthesis, style transfer, frame interpolation, fluid prediction, and fluid editing, which illustrate the practical value of GaussFluids.en_US
dc.description.sectionheadersPoint Clouds & Gaussian Splatting
dc.description.seriesinformationPacific Graphics Conference Papers, Posters, and Demos
dc.identifier.doi10.2312/pg.20251286
dc.identifier.isbn978-3-03868-295-0
dc.identifier.pages13 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20251286
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20251286
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 → Computer graphics; Machine learning; Modeling and simulation
dc.subjectComputing methodologies → Computer graphics
dc.subjectMachine learning
dc.subjectModeling and simulation
dc.titleGaussFluids: Reconstructing Lagrangian Fluid Particles from Videos via Gaussian Splattingen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20251286.pdf
Size:
16.32 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2025 Conference Papers, Posters, and Demos