arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.13541cs.GR
收藏

DDPM-Polycube:一种用于基于多立方体的六面体网格生成与体样条构造的去噪扩散概率模型

DDPM-Polycube: A Denoising Diffusion Probabilistic Model for Polycube-Based Hexahedral Mesh Generation and Volumetric Spline Construction

Yuxuan Yu, Yuzhuo Fang, Hua Tong, Jiashuo Liu, Yongjie Jessica Zhang

AI总结:

提出 DDPM-Polycube,将几何到多立方体的变形视为 DDPM 去噪任务,以生成六面体网格并构造满足 IGA 要求的体样条,且对训练范围外拓扑具有泛化性。

摘要:

本文提出 DDPM-Polycube,这是一种基于去噪扩散概率模型(DDPM)的生成式多立方体创建方法,用于生成高质量六面体(hex)网格并构造体样条。与依赖预定义多立方体结构模板的 DL-Polycube 方法不同,DDPM-Polycube 将从输入几何到其相应多立方体结构的变形建模为一项去噪任务。通过学习简单几何基元(一个立方体和一个带孔立方体)的变形特征,DDPM-Polycube 模型通过去除非标准高斯噪声,从输入几何逐步重建多立方体结构。一旦生成有效的多立方体结构,这些结构便被用于曲面分割和参数映射,以生成高质量六面体网格。随后,采用截断层次 B 样条构造满足等几何分析(IGA)要求的体样条。实验结果表明,DDPM-Polycube 模型能够直接从输入几何生成多立方体结构,即使这些几何的拓扑超出其训练范围也是如此。这为多样化的工程几何提供了更强的泛化能力和适应性。总体而言,本研究展示了扩散模型在推进网格生成和 IGA 应用方面的潜力。

英文摘要:

In this paper, we propose DDPM-Polycube, a generative polycube creation approach based on denoising diffusion probabilistic models (DDPM) for generating high-quality hexahedral (hex) meshes and constructing volumetric splines. Unlike DL-Polycube methods that rely on predefined polycube structure templates, DDPM-Polycube models the deformation from input geometry to its corresponding polycube structures as a denoising task. By learning the deformation characteristics of simple geometric primitives (a cube and a cube with a hole), the DDPM-Polycube model progressively reconstructs polycube structures from input geometry by removing non-standard Gaussian noise. Once valid polycube structures are generated, they are used for surface segmentation and parametric mapping to generate high-quality hex meshes. Truncated hierarchical B-splines are then applied to construct volumetric splines that satisfy the requirements of isogeometric analysis (IGA). Experimental results demonstrate that DDPM-Polycube model can directly generate polycube structures from input geometries, even when the topology of these geometries falls outside its trained range. This provides greater generalization and adaptability for diverse engineering geometries. Overall, this research shows the potential of diffusion models in advancing mesh generation and IGA applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑