Masked Topology Modeling for Self-Supervised Learning on Parametric CAD

参数化 CAD 自监督学习的掩码拓扑建模

Computer aided design (CAD) is ubiquitous: virtually any modern object was designed using editable CAD tools. However, with the shortage of available CAD datasets in its native editable and parametric format, boundary representation (B-Rep), it is ever more important to develop data-efficient methods for this domain.

计算机辅助设计（CAD）无处不在：几乎所有现代物体都是使用可编辑的 CAD 工具设计的。然而，由于缺乏以原生可编辑和参数化格式（即边界表示，B-Rep）呈现的 CAD 数据集，为该领域开发数据高效的方法变得愈发重要。

We present a new self-supervised pretraining task, Masked Topology Modeling (MTM), that leverages the face-adjacency graph, an induced structure unique to B-reps that the encoder can be asked to reconstruct. MTM masks a fraction of edges and trains a small head to predict each masked edge’s convexity and curve type from the encoder’s post-message-passing face features.

我们提出了一种新的自监督预训练任务——掩码拓扑建模（Masked Topology Modeling, MTM）。该任务利用了面邻接图（face-adjacency graph），这是一种 B-Rep 特有的诱导结构，编码器可以通过重构该结构进行学习。MTM 会掩盖一部分边，并训练一个小型头部网络，根据编码器在消息传递后的面特征，预测每个被掩盖边的凸凹性和曲线类型。

We combine MTM with a MoCo-style momentum-queue contrastive learning over B-rep-aware augmentations, a BFS-connected face-region masked-reconstruction objective, and pretraining on the ABC dataset and our new procedurally generated dataset to show strong performance on a number of benchmarks.

我们将 MTM 与基于 B-Rep 感知增强的 MoCo 风格动量队列对比学习、基于广度优先搜索（BFS）连接的面区域掩码重构目标相结合，并在 ABC 数据集以及我们新生成的程序化数据集上进行预训练，从而在多个基准测试中展现出强大的性能。