Scalable DDPM-Polycube: An Extended Diffusion-Based Method for Hexahedral Mesh and Volumetric Spline Construction

2026-04-19

AI Summary

Existing learning-based Polycube methods are limited in handling complex CAD geometries due to insufficient primitive diversity, low-dimensional grid configurations, and high inference costs. This work proposes a scalable diffusion model–driven framework that introduces a novel blind-hole cube primitive to capture local voids, extends grid configuration from two to three dimensions, and incorporates a genus-guided context generation and hierarchical validation mechanism. The approach substantially enhances model expressiveness and automation, enabling efficient synthesis of high-fidelity Polycube structures suitable for full hexahedral meshing and volumetric spline construction required in isogeometric analysis. Significant improvements are achieved in both geometric fidelity and computational efficiency.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Polycube structures provide parametric domains for all-hexahedral (all-hex) mesh generation and analysis-suitable volumetric spline construction in isogeometric analysis (IGA). Recent learning-based polycube pipelines have improved automation, yet several challenges remain when handling complex CAD geometries. These challenges include the limited diversity of primitive geometries, restricted grid configurations, and the increasing cost of genus-guided context search during inference as both the primitive set and the grid size grow. In this paper, we present {Scalable DDPM-Polycube}, an extended diffusion-based polycube construction method that addresses these limitations. First, we expand the primitive set from two primitive geometries to three by introducing a blind-hole cube primitive, thereby improving the representation of local hole-like features that do not change the global genus. Second, we extend the grid configuration from the previous $2\times 1$ setting to an enlarged three-dimensional grid configuration, which increases representational capacity and reduces mapping distortion for complex geometries. Third, we develop a genus-guided context generation strategy together with a hierarchical verification procedure, enabling robust context generation in both user-guided and automated modes. Once a valid polycube structure is generated, it is used for parametric mapping, all-hex control mesh generation, and volumetric spline construction. Experimental results demonstrate that scalable DDPM-Polycube improves the generality, scalability, and automation of diffusion-based polycube generation, and supports hex mesh generation and volumetric spline construction for IGA applications on complex geometries.

Problem

• polycube
• hexahedral mesh
• volumetric spline
• CAD geometry
• genus-guided context

Innovation

• diffusion-based polycube
• hexahedral mesh generation
• volumetric spline
• genus-guided context
• scalable grid configuration