Score: 0

VoroLight: Learning Quality Volumetric Voronoi Meshes from General Inputs

Published: December 15, 2025 | arXiv ID: 2512.12984v1

By: Jiayin Lu , Ying Jiang , Yin Yang and more

Potential Business Impact:

Builds 3D shapes from pictures and points.

Business Areas:
Virtual Reality Hardware, Software

We present VoroLight, a differentiable framework for 3D shape reconstruction based on Voronoi meshing. Our approach generates smooth, watertight surfaces and topologically consistent volumetric meshes directly from diverse inputs, including images, implicit shape level-set fields, point clouds and meshes. VoroLight operates in three stages: it first initializes a surface using a differentiable Voronoi formulation, then refines surface quality through a polygon-face sphere training stage, and finally reuses the differentiable Voronoi formulation for volumetric optimization with additional interior generator points. Project page: https://jiayinlu19960224.github.io/vorolight/

Country of Origin
🇺🇸 United States

Page Count
20 pages

Category
Computer Science:
Computational Geometry