Summer School on Reduced Order Methods in Computational Fluid Dynamics

Machine Learning and Optimal Transport for shape parametrisation

Not scheduled

20m

SISSA, International School for Advanced Studies, Main Campus, Trieste, Italy

Poster Poster blitz

Speaker

Guglielmo Padula (Internship at Sissa MathLab)

Description

This work focuses on the application of methods of 3D mesh deformation in order to preserve properties of interest like volume or curvature. Results regarding Variational Autoencoders, Semi-Discrete Optimal Transport applied to simple geometries will be presented. The extension of Semi Discrete Optimal Transport to three meshes will also be discussed.