← Papers

CNN steady flow

Convolutional Neural Networks for Steady Flow Approximation

Paper title Convolutional Neural Networks for Steady Flow Approximation

Guo et al. (University of Michigan and Autodesk Research) · Aero & CFD

Paper doi.org⁠

Encodes the shape as a signed distance function sampled on a Cartesian grid and passes it through a convolutional encoder–decoder that returns the whole steady velocity field in one forward pass, in 2D or 3D.

Published
KDD

Share on LinkedIn, X or Bluesky, or or .

Know related work that belongs here?

Something wrong on this page?

More papers

All papers
  1. PhysicsNeMo-Mesh — GPU-Native Meshes and Simulation Cases for Physics AI
  2. Multi-fidelity scaling — Compute-optimal data scaling via multi-fidelity training
  3. CAE-UQ — Predictive Uncertainty for Neural CAE Surrogates