← Papers
Graphs

Geodesic CNN shape optimisation

Geodesic Convolutional Shape Optimization

Paper title Geodesic Convolutional Shape Optimization

Baqué et al. (EPFL) · Aero & CFD

Paper arXiv 1802.04016PDF

Trains a geodesic convolutional network directly on surface meshes to emulate a CFD solver (pressure and drag), after remeshing shapes with a polycube map so it runs on GPUs. Because the network is differentiable, drag can be minimised with gradients with respect to the shape, under constraints such as room for engine and passengers.

Published
ICML

Share on LinkedIn, X or Bluesky, or or .

Know related work that belongs here?

Something wrong on this page?

More papers

All papers
  1. GraphsR-BiLoGo — Transfer learning for rib effects in sheet-forming surrogates
  2. GraphsRead-Write-Relax — Why neural PDE surrogates need both global and local processing
  3. GraphsDGN / LDGN — Sampling flow distributions on meshes with diffusion graph networks