arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.01873cs.GRcs.CVcs.LG
收藏

NeuralMLS:几何感知控制点变形

NeuralMLS: Geometry-Aware Control Point Deformation

Tel-Aviv University(特拉维夫大学);University of Chicago(芝加哥大学)

Meitar Shechter, Rana Hanocka, Gal Metzer, Raja Giryes, Daniel Cohen-Or

摘要:

我们介绍NeuralMLS,一种基于空间的变形技术,由一组位移控制点指导。我们利用神经网络的力量,注入到变形参数的基本形状几何。我们的技术的目标是使一个现实和直观的形状变形。我们的方法是建立在移动最小二乘(MLS),因为它最小化给定的控制点位移的加权和。传统上,每个控制点对空间中每个点的影响(即,加权函数)是使用反距离几何学来定义的。在这项工作中,我们选择学习加权函数,通过训练一个神经网络的控制点,从一个单一的输入形状,并利用先天的光滑神经网络。我们的几何感知控制点变形与表面表示和质量无关;它可以应用于点云或网格,包括非流形和断开的表面汤。我们表明,我们的技术有利于直观的分段平滑变形,这是非常适合制造的对象。我们展示了我们的方法相比,现有的表面和基于空间的变形技术,定量和定性的优势。

英文摘要:

We introduce NeuralMLS, a space-based deformation technique, guided by a set of displaced control points. We leverage the power of neural networks to inject the underlying shape geometry into the deformation parameters. The goal of our technique is to enable a realistic and intuitive shape deformation. Our method is built upon moving least-squares (MLS), since it minimizes a weighted sum of the given control point displacements. Traditionally, the influence of each control point on every point in space (i.e., the weighting function) is defined using inverse distance heuristics. In this work, we opt to learn the weighting function, by training a neural network on the control points from a single input shape, and exploit the innate smoothness of neural networks. Our geometry-aware control point deformation is agnostic to the surface representation and quality; it can be applied to point clouds or meshes, including non-manifold and disconnected surface soups. We show that our technique facilitates intuitive piecewise smooth deformations, which are well suited for manufactured objects. We show the advantages of our approach compared to existing surface and space-based deformation techniques, both quantitatively and qualitatively.

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。

↑