arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.14656math.NAcs.NA
收藏

一种结合最小化运动和神经网络的方法用于Willmore流

A hybrid minimizing movement and neural network approach to Willmore flow

University of Bonn(波恩大学);ENS Paris-Saclay(巴黎萨克雷高等师范学院)

Martin Rumpf, Josua Sassen, Christoph Smoch

AI总结:

本文提出了一种结合最小化运动和神经网络的混合方法,用于高效模拟Willmore流,通过神经近似平均曲率流提升计算效率,并在表面平滑和形状重建中展现有效性。

摘要:

我们提出了一种结合最小化运动方案与神经算子的混合方法,用于相场基Willmore流的模拟。最小化运动部分基于标准优化问题在规则网格上的求解,而需最小化的函数涉及Bretin等人提出的神经近似平均曲率流。数值实验证实了该方法在大时间步长下的稳定性、一致性和与传统有限元方法相比显著降低的计算成本。此外,应用显示其在表面平滑和损坏形状重建中的有效性。因此,该方法为几何处理提供了一种稳健且高效的工具。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑