Presentation

<
Gaussian Fluids: A Grid-Free Fluid Solver based on Gaussian Spatial Representation
SessionThis is Fluid Simulation
DescriptionWe present a grid-free fluid simulator featuring a novel Gaussian spatial representation (GSR) for velocity field. The advantages of GSR over traditional Lagrangian/Eulerian data structures are 4-folded: memory compactness, spatial adaptivity, vorticity preservation and continuous differentiability. Our method also greatly outperforms similar competitors in terms of quality and performance.
Authors
Jingrui Xing
School of Intelligence Science and Technology, Peking University
Bin Wang
Independent
Mengyu Chu
Peking University
State Key Laboratory of General Artificial Intelligence
Baoquan Chen
Peking University
State Key Laboratory of General Artificial Intelligence
Event Type
Technical Paper
TimeMonday, 11 August 20259:20am - 9:30am PDT
LocationWest Building, Rooms 220-222
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Monday, 11 August 20259:00am - 10:30am PDTWest Building, Rooms 220-222
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationQuadtree Tall Cells for Eulerian Liquid Simulation
Similar Presentations
Fast Subspace Fluid Simulation with a Temporally-Aware Basis
Fluid Simulation on Vortex Particle Flow Maps
Cirrus: Adaptive Hybrid Particle-Grid Flow Maps on GPU