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.
Learning the Willmore flow with a lightweight neural operator
INSA Lyon, CNRS, Ecole Centrale de Lyon, Université Claude Bernard Lyon 1, Université Jean Monnet, ICJ UMR5208(里昂国立应用科学学院,法国国家科学研究中心,里昂中央理工学院,里昂第一大学,让·莫内大学,ICJ联合研究实验室)
Simulation of multiphase porous media flows with minimizing movement and finite volume schemes
Inria, Univ. Lille, CNRS, UMR 8524 - Laboratoire Paul Painlevé(法国国家信息与自动化研究所,里尔大学,法国国家科学研究中心);Inria, Project team MOKAPLAN and Mathematics department, Université de Liège(法国国家信息与自动化研究所,列日大学);Department of Mathematics and Statistics, McGill University(麦吉尔大学数学与统计系);IECL Université de Lorraine(洛林大学计算数学与复杂系统研究所);GFM Universidade de Lisboa(里斯本大学)
A deep implicit-explicit minimizing movement method for option pricing in jump-diffusion models
Department of Mathematics(数学系);The Maxwell Institute for Mathematical Sciences, Heriot-Watt University(数学科学研究所,赫瑞斯泰大学);National Technical University of Athens(雅典技术大学);Institute of Applied and Computational Mathematics, FORTH(应用与计算数学研究所,FORTH);Delft Institute of Applied Mathematics, TU Delft(应用数学研究所,代尔夫特理工大学);University of the Aegean(爱琴海大学)