arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.26964cs.CGcs.LG
收藏

神经近似通用Voronoi图

Neural Approximation of Generalized Voronoi Diagrams

National and Kapodistrian University of Athens(雅典大学);Athena Research Center(雅典娜研究中心);Institute for Language and Speech Processing, Athena Research Center(雅典娜研究中心语言与语音处理研究所)

Panagiotis Rigas, George Ioannakis, Ioannis Emiris

AI总结:

本文提出VoroFields框架,通过神经场近似有限几何站点集的通用Voronoi图,利用连续可微代理学习实现隐式分区,实验显示无需特定形状构造即可准确恢复细胞和边界几何。

摘要:

我们引入VoroFields,一种分层神经场框架,用于在低维领域中近似有限几何站点集的通用Voronoi图,采用可评估的点到站点距离。不同于组合构造,VoroFields学习连续可微代理,其最大化结构隐式诱导分区。Voronoi单元对应场的最大化区域,边界由竞争站点的相等响应定义。分层分解通过仅在包络过渡结构附近细化,降低组合复杂性。实验显示在不同站点家族和度量下,无需特定形状构造即可准确恢复单元和边界几何。

英文摘要:

We introduce VoroFields, a hierarchical neural-field framework for approximating generalized Voronoi diagrams of finite geometric site sets in low-dimensional domains under arbitrary evaluable point-to-site distances. Instead of constructing the diagram combinatorially, VoroFields learns a continuous, differentiable surrogate whose maximizer structure induces the partition implicitly. The Voronoi cells correspond to maximizer regions of the field, with boundaries defined by equal responses between competing sites. A hierarchical decomposition reduces the combinatorial complexity by refining only near envelope transition strata. Experiments across site families and metrics demonstrate accurate recovery of cells and boundary geometry without shape-specific constructions.

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。

↑