Self-Supervised Representation Learning for CAD
This addresses the challenge of data scarcity for machine learning in CAD design, enabling better assistance in engineering and manufacturing, though it is incremental as it builds on existing datasets and benchmarks.
The paper tackles the problem of limited labeled data in CAD's native B-Rep format by proposing a self-supervised pre-training method using unlabeled CAD geometry, resulting in significant improvements in few-shot learning and state-of-the-art performance on existing benchmarks.
The design of man-made objects is dominated by computer aided design (CAD) tools. Assisting design with data-driven machine learning methods is hampered by lack of labeled data in CAD's native format; the parametric boundary representation (B-Rep). Several data sets of mechanical parts in B-Rep format have recently been released for machine learning research. However, large scale databases are largely unlabeled, and labeled datasets are small. Additionally, task specific label sets are rare, and costly to annotate. This work proposes to leverage unlabeled CAD geometry on supervised learning tasks. We learn a novel, hybrid implicit/explicit surface representation for B-Rep geometry, and show that this pre-training significantly improves few-shot learning performance and also achieves state-of-the-art performance on several existing B-Rep benchmarks.