摘要
在CAD领域,边界表示(B-rep)因其精确性被广泛采用,但其非结构化特性使基于B-rep的深度学习模型较少。现有方法多侧重几何信息的描述,虽提升性能,却增加了复杂度和数据提取成本,且对拓扑信息关注不足,限制了模型的泛化能力和整体表现。为解决上述问题,本文提出了一种基于层次掩码及多尺度特征融合的CAD模型表征网络,同时支持模型分类和分割。具体而言,通过设计层次掩码几何编码器来消除信息冗余,减少网络对信息的过度依赖,提高了网络的鲁棒性和泛化性;同时,通过设计多尺度自适应拓扑编码器来自适应地提取多尺度特征,能够捕获从局部到全局的拓扑结构信息。广泛实验证明了新模型在多个公开分类和分割数据集上的先进性和有效性。
In CAD,B-rep is widely used for its precise representation,but its unstructured nature limits deep learning models based on it.Existing methods focus heavily on geometric information,improving performance but increasing complexity and data cost,while insufficient topology attention restricts generalization and overall effectiveness.To address the above issues,a hierarchical mask and multi-scale feature fusion-based network was proposed,which supported both model classification and segmentation.Specifically,a hierarchical mask geometric encoder was designed to eliminate information redundancy,reducing the network′s over-reliance on information and enhancing robustness and generalization.Furthermore,a multi-scale adaptive topological encoder was introduced to adaptively extract multi-scale features,capturing topological structure information from local to global.Extensive experiments demonstrated the advanced performance and effectiveness of the new model on multiple public classification and segmentation datasets.
作者
苏增辉
马向宇
白静
林淦
SU Zenghui;MA Xiangyu;BAI Jing;LIN Gan(Department of Computer Science and Engineering,North Minzu University,Yinchuan 750021,China;Key Laboratory of Image and Graphics Intelligent Processing,State Ethnic Affairs Commission,North Minzu University,Yinchuan 750021,China)
出处
《计算机集成制造系统》
北大核心
2025年第8期2843-2856,共14页
Computer Integrated Manufacturing Systems
基金
国家自然科学基金资助项目(62162001)
宁夏自然科学基金资助项目(2022AAC02041)
宁夏优秀人才支持计划项目(NCCA2025)。
关键词
边界表示
模型分类
分割
图卷积神经网络
掩码
拓扑
boundary representation
model classification
segmentation
graph convolutional neural network
mask
topology
作者简介
苏增辉(2000-),男,河南新乡人,硕士研究生,研究方向:CAD和深度学习,E-mail:huixiaoge2023@163.com;马向宇(1998-),男,河南驻马店人,硕士研究生,研究方向:CAD和深度学习,E-mail:maxiangyu_nun@163.com;通讯作者:白静(1982-),女,宁夏青铜峡人,教授,博士,研究方向:CAD&CG和深度学习,E-mail:baijing_nun@163.com;林淦(1998-),男,浙江宁波人,硕士研究生,研究方向:深度表征学习,E-mail:lingan_nun@163.com。
