发表机构
StoryGold AI（故事黄金人工智能公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对缺乏原生可编辑和参数化格式CAD数据集的问题，提出掩码拓扑建模（MTM）自监督预训练任务，结合多种方法在相关数据集预训练，在多个基准测试中表现出色。
AI 中文摘要
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，由于缺乏原生可编辑和参数化格式（边界表示，即B-Rep）的CAD数据集，为该领域开发数据高效的方法变得越发重要。我们提出了一种新的自监督预训练任务——掩码拓扑建模（MTM），它利用面邻接图（一种B-Rep特有的诱导结构）让编码器进行重建。MTM会屏蔽一部分边，并训练一个小的头部从编码器的消息传递后的面特征预测每个屏蔽边的凸性和曲线类型。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、一个BFS连接的面区域掩码重建目标相结合，并在ABC数据集和新的程序生成数据集上进行预训练，在多个基准测试中展现出强大性能。
英文摘要
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. 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. 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.
