JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints
This addresses the challenge of automating assembly in CAD design for engineers and designers, representing a strong specific gain in this domain.
The paper tackles the problem of assembling 3D parts in CAD software using constraints called joints, and introduces JoinABLe, a learning-based method that achieves 79.53% accuracy, approaching human performance at 80%.
Physical products are often complex assemblies combining a multitude of 3D parts modeled in computer-aided design (CAD) software. CAD designers build up these assemblies by aligning individual parts to one another using constraints called joints. In this paper we introduce JoinABLe, a learning-based method that assembles parts together to form joints. JoinABLe uses the weak supervision available in standard parametric CAD files without the help of object class labels or human guidance. Our results show that by making network predictions over a graph representation of solid models we can outperform multiple baseline methods with an accuracy (79.53%) that approaches human performance (80%). Finally, to support future research we release the Fusion 360 Gallery assembly dataset, containing assemblies with rich information on joints, contact surfaces, holes, and the underlying assembly graph structure.