Neural Approximation of Generalized Voronoi Diagrams

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rigas, Panagiotis, Ioannakis, George, Emiris, Ioannis
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911549592961024
author Rigas, Panagiotis
Ioannakis, George
Emiris, Ioannis
author_facet Rigas, Panagiotis
Ioannakis, George
Emiris, Ioannis
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26964
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural Approximation of Generalized Voronoi Diagrams
Rigas, Panagiotis
Ioannakis, George
Emiris, Ioannis
Computational Geometry
Machine Learning
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.
title Neural Approximation of Generalized Voronoi Diagrams
topic Computational Geometry
Machine Learning
url https://arxiv.org/abs/2603.26964