Neural Centroidal Voronoi Tessellations
Open Access
- 9 November 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-14
Abstract
Centroidal Voronoi tessellation (CVT) is a fundamental primitive for high-quality surface sampling and isotropic remeshing in computer graphics. However, computing surface CVTs with classical solvers remains expensive: each optimization step repeatedly constructs restricted Voronoi diagrams (RVDs) and integrates quantities over their surface cells. We introduce Neural CVT , a learning-based surface-CVT solver that replaces these costly geometric computations with a recurrent neural optimizer, accelerating CVT optimization by one to two orders of magnitude in our benchmarks while preserving geometric fidelity. Given an input surface, we sample a dense point cloud and extract multi-scale geometric descriptors with a graph neural encoder. A lightweight recurrent optimizer then refines seed positions over a small number of iterations, aggregating interpolated surface features and optimization history to predict per-seed displacements. The framework is trained self-supervised using CVT objectives that promote uniform distributions and, when desired, feature alignment. Across diverse organic and CAD-like shapes, Neural CVT generalizes to unseen geometry, initialization strategies, and seed densities, producing isotropic, feature-preserving remeshes comparable to state-of-the-art offline optimization methods at a fraction of the computational cost. The code and trained models are available at https://github.com/sig-pku/NeuralCVT.Keywords
This publication has 8 references indexed in Scilit:
- Dual octree graph networks for learning adaptive volumetric shape representationsACM Transactions on Graphics, 2022
- DiffusionNet: Discretization Agnostic Learning on SurfacesACM Transactions on Graphics, 2022
- MeshCNNACM Transactions on Graphics, 2019
- Optimal voronoi tessellations with hessian-based anisotropyACM Transactions on Graphics, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Instant field-aligned meshesACM Transactions on Graphics, 2015
- On centroidal voronoi tessellation—energy smoothness and fast computationACM Transactions on Graphics, 2009
- A remeshing approach to multiresolution modeling2004