Saved in:
Bibliographic Details
Main Authors: Rumpf, Martin, Sassen, Josua, Smoch, Christoph
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.14656
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914322575261696
author Rumpf, Martin
Sassen, Josua
Smoch, Christoph
author_facet Rumpf, Martin
Sassen, Josua
Smoch, Christoph
contents We present a hybrid method combining a minimizing movement scheme with neural operators for the simulation of phase field-based Willmore flow. The minimizing movement component is based on a standard optimization problem on a regular grid whereas the functional to be minimized involves a neural approximation of mean curvature flow proposed by Bretin et al. Numerical experiments confirm stability for large time step sizes, consistency and significantly reduced computational cost compared to a traditional finite element method. Moreover, applications demonstrate its effectiveness in surface fairing and reconstructing of damaged shapes. Thus, the approach offers a robust and efficient tool for geometry processing.
format Preprint
id arxiv_https___arxiv_org_abs_2502_14656
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A hybrid minimizing movement and neural network approach to Willmore flow
Rumpf, Martin
Sassen, Josua
Smoch, Christoph
Numerical Analysis
We present a hybrid method combining a minimizing movement scheme with neural operators for the simulation of phase field-based Willmore flow. The minimizing movement component is based on a standard optimization problem on a regular grid whereas the functional to be minimized involves a neural approximation of mean curvature flow proposed by Bretin et al. Numerical experiments confirm stability for large time step sizes, consistency and significantly reduced computational cost compared to a traditional finite element method. Moreover, applications demonstrate its effectiveness in surface fairing and reconstructing of damaged shapes. Thus, the approach offers a robust and efficient tool for geometry processing.
title A hybrid minimizing movement and neural network approach to Willmore flow
topic Numerical Analysis
url https://arxiv.org/abs/2502.14656