通过掩码拓扑建模，让CAD模型自监督学习更高效。
Masked Topology Modeling for Self-Supervised Learning on Parametric CAD
- 用面邻接图掩码边并预测凸性与曲线类型，实现自监督预训练。
- 在ABC和新生成数据集上预训练，多个基准测试表现优异。
- 适合做参数化CAD模型表示学习的研究者和工业界应用者。
计算机辅助设计（CAD）无处不在：几乎所有现代产品都使用可编辑的参数化CAD工具设计。然而，由于原生可编辑、参数化格式的CAD数据集稀缺，边界表示（B-Rep）领域亟需数据高效的算法。本文提出一种新的自监督预训练任务——掩码拓扑建模（MTM），利用B-Rep特有的面邻接图结构，让编码器重建被掩码的边。MTM通过掩码部分边，训练一个小头部根据编码器处理后的面特征预测每条被掩码边的凸性与曲线类型。我们结合基于动量队列的对比学习（MoCo风格）、基于广度优先搜索连通面区域的掩码重建目标，并在ABC数据集及新生成的程序化数据集上进行预训练，显著提升多个下游任务的表现。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。