CAD模型编码新方法提升神经网络稳定性
Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations
想用AI处理CAD模型的朋友看过来,这个新方法能解决模型表示不一致导致的问题,让AI处理更稳定。
边界表示(B-rep)是现代CAD系统的标准格式,但同一实体可能存在多种表示。现有B-rep编码器对标准基准测试中的扰动、CAD软件固有差异以及设计师建模方式的变化不稳健,性能会崩溃。
本文提出基于实体的规范区域图(canonical region graph)表示方法,其节点、特征和坐标系由实体本身定义,具有理论上的不变性保证,在所有测试扰动下都保持稳定。
Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations
Boundary representation (B-rep) is the standard format used by modern CAD systems for parametric 3D models. It turns out, the exact same solid can be represented by different B-reps: for example, two engineers using different operations, a geometry kernel rebuilding the file, and an export setting repartitioning faces will lead to different B-reps even though the underlying solid remains the same. We show that existing B-rep encoders are not robust to variation in the B-rep with the same solid on perturbations applied to standard benchmarks, naturally occurring variations inherent to CAD software, and differences in how designers model the same part via a human dataset we created in FreeCAD. The performance of popular B-rep encoders often collapses catastrophically. We propose the canonical region graph, an input representation whose nodes, features and coordinate frame are derived from the solid itself and show theoretical invariance guarantees on repartitioning and rigid motions. It matches the strongest baseline on standard benchmarks, and is stable under every perturbation we test.
本条情报归属 AITOP「论文」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:CAD、B-rep、神经网络、模型稳定性,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Heinrich Jiang, Hager Yasser Mohamed, Alexander Hitt, Valeriia Lomakina, Henning Jiang, Jennifer Jang),经 AITOP 多维评分管线结构化提炼。