VoroLight: Learning Quality Volumetric Voronoi Meshes from General Inputs
This work addresses the problem of creating high-quality volumetric meshes for applications in computer graphics and 3D modeling, representing an incremental improvement over existing methods.
The authors tackled 3D shape reconstruction by developing VoroLight, a differentiable framework that generates smooth, watertight surfaces and topologically consistent volumetric meshes from diverse inputs like images and point clouds, achieving high-quality results as demonstrated in their experiments.
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/