arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.07429cs.LGcs.AI
收藏

Brep2Shape:通过自监督变换器对齐边界与形状表示

Brep2Shape: Boundary and Shape Representation Alignment via Self-Supervised Transformers

School of Software, BNRist, Tsinghua University(清华大学软件学院)

Yuanxu Sun, Yuezhou Ma, Haixu Wu, Guanyang Zeng, Muye Chen, Jianmin Wang, Mingsheng Long

AI总结:

提出Brep2Shape自监督预训练方法,利用双Transformer骨干和拓扑注意力对齐B-rep的抽象边界表示与直观形状表示,在多项下游任务中达到最优精度并加速收敛。

摘要:

边界表示(B-rep)是计算机辅助设计(CAD)的行业标准。虽然深度学习在处理B-rep模型方面显示出潜力,但现有方法存在表示差距:连续方法提供分析精度但视觉上抽象,而离散方法提供直观清晰性但牺牲了几何精度。为弥合这一差距,我们引入了Brep2Shape,一种新颖的自监督预训练方法,旨在对齐抽象边界表示与直观形状表示。我们的方法采用几何感知任务,其中模型学习从参数化贝塞尔控制点预测密集空间点,使网络能够更好地理解从抽象系数导出的物理流形。为增强这种对齐,我们提出了一个双Transformer骨干,具有并行流,独立编码表面和曲线令牌以捕获它们不同的几何属性。此外,集成了拓扑注意力以建模表面和曲线之间的相互依赖关系,从而保持拓扑一致性。实验结果表明,Brep2Shape具有显著的可扩展性,在各种下游任务中实现了最先进的精度和更快的收敛速度。代码可在以下仓库获取:this https URL。

英文摘要:

Boundary representation (B-rep) is the industry standard for computer-aided design (CAD). While deep learning shows promise in processing B-rep models, existing methods suffer from a representation gap: continuous approaches offer analytical precision but are visually abstract, whereas discrete methods provide intuitive clarity at the expense of geometric precision. To bridge this gap, we introduce Brep2Shape, a novel self-supervised pre-training method designed to align abstract boundary representations with intuitive shape representations. Our method employs a geometry-aware task where the model learns to predict dense spatial points from parametric Bézier control points, enabling the network to better understand physical manifolds derived from abstract coefficients. To enhance this alignment, we propose a Dual Transformer backbone with parallel streams that independently encode surface and curve tokens to capture their distinct geometric properties. Moreover, the topology attention is integrated to model the interdependencies between surfaces and curves, thereby maintaining topological consistency. Experimental results demonstrate that Brep2Shape offers significant scalability, achieving state-of-the-art accuracy and faster convergence across various downstream tasks.Code is available at this repository: https://github.com/thuml/Brep2Shape.

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。

↑