arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.07973cs.CV
收藏

深度程函解算器

Deep Eikonal Solvers

Technion - Israel Institute of Technology(以色列理工学院)

Moshe Lichtenstein, Gautam Pai, Ron Kimmel

摘要:

介绍了一种深度学习方法来数值近似Eikonal方程的解。所提出的方法是建立在快速推进计划,其中包括两个组成部分:一个本地数值求解器和更新计划。我们取代公式化的本地数值求解器与训练的神经网络,以提供高度准确的估计各种不同的几何形状和采样条件的本地距离。我们的学习方法不仅推广到平坦的欧几里德域,而且还通过在神经网络架构中引入某些不变特征来实现曲面。我们表现出相当大的增益的性能,验证了较小的误差和更高的精度阶的Eikonal方程的数值解计算在不同的表面上所提出的方法利用神经网络的近似能力,以提高数值算法的性能,从而,连接有点不同的主题的数值几何和学习。

英文摘要:

A deep learning approach to numerically approximate the solution to the Eikonal equation is introduced. The proposed method is built on the fast marching scheme which comprises of two components: a local numerical solver and an update scheme. We replace the formulaic local numerical solver with a trained neural network to provide highly accurate estimates of local distances for a variety of different geometries and sampling conditions. Our learning approach generalizes not only to flat Euclidean domains but also to curved surfaces enabled by the incorporation of certain invariant features in the neural network architecture. We show a considerable gain in performance, validated by smaller errors and higher orders of accuracy for the numerical solutions of the Eikonal equation computed on different surfaces The proposed approach leverages the approximation power of neural networks to enhance the performance of numerical algorithms, thereby, connecting the somewhat disparate themes of numerical geometry and learning.

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。

↑