Presentation

<
A Neural Particle Level Set Method for Dynamic Interface Tracking
SessionThis is Fluid Simulation
DescriptionWe propose Neural PLS, a neural particle level-set method for tracking and evolving dynamic neural representations. Oriented particles serve as interface trackers and sampling seeders, enabling efficient evolution on a multi-resolution grid-hash structure. Our approach integrates traditional PLS and implicit neural representations, achieving superior performance in benchmarks and physical simulations.
Authors
Duowen Chen
Georgia Institute of Technology
Junwei Zhou
University of Michigan
Bo Zhu
Georgia Institute of Technology
Presenter
Duowen Chen
Georgia Institute of Technology
Event Type
Technical Paper
TimeMonday, 11 August 20259:40am - 9:50am PDT
LocationWest Building, Rooms 220-222
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 PresentationThis is Fluid Simulation - Interactive Discussion
Similar Presentations
Fluid Simulation on Vortex Particle Flow Maps
Neural Importance Sampling of Many Lights
Patch-Grid: An Efficient and Feature-Preserving Neural Implicit Surface Representation