Research map / 3D vision / Face and shape
Neural Fluid Simulation on Geometric Surfaces
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a neural solver for incompressible fluid simulation on 3D geometric surfaces that addresses extending physical laws to surfaces and preserving energy and volume.
Problem
Simulating incompressible fluids on 3D surfaces, which requires extending physical laws onto curved surfaces while preserving energy and volume; traditional grid- or mesh-based methods struggle with this.
Approach
Neural fluid simulation directly on geometric surfaces, as an alternative to grid- or mesh-based traditional solvers, designed to respect surface physics and conserve energy and volume. Full method details are not available from the abstract.
Closest papers by meaning
- An Intrinsic Vector Heat Network (ICML 2024 · similarity 0.87)
- Neural Physical Simulation with Multi-Resolution Hash Grid Encoding (AAAI 2024 · similarity 0.84)
- MeshMask: Physics-Based Simulations with Masked Graph Neural Networks (ICLR 2025 · similarity 0.84)
- Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics (ICLR 2024 · similarity 0.84)
- HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction (ICML 2024 · similarity 0.84)
- From Zero to Turbulence: Generative Modeling for 3D Flow Simulation (ICLR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.