SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design

Abstract

Parametric computer-aided design (CAD) is the dominant paradigm in mechanical engineering for physical design. Distinguished by relational geometry, parametric CAD models begin as two-dimensional sketches consisting of geometric primitives (e.g., line segments, arcs) and explicit constraints between them (e.g., coincidence, perpendicularity) that form the basis for three-dimensional construction operations. Training machine learning models to reason about and synthesize parametric CAD designs has the potential to reduce design time and enable new design workflows. Additionally, parametric CAD designs can be viewed as instances of constraint programming and they offer a well-scoped test bed for exploring ideas in program synthesis and induction. To facilitate this research, we introduce SketchGraphs, a collection of 15 million sketches extracted from real-world CAD models coupled with an open-source data processing pipeline. Each sketch is represented as a geometric constraint graph where edges denote designer-imposed geometric relationships between primitives, the nodes of the graph. We demonstrate and establish benchmarks for two use cases of the dataset: generative modeling of sketches and conditional generation of likely constraints given unconstrained geometry.

References in corpus (10)

• Distributed Representations of Words and Phrases and their Compositionality
• Neural Message Passing for Quantum Chemistry
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Link Prediction in Complex Networks: A Survey
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• A Neural Representation of Sketch Drawings
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• Learning Deep Generative Models of Graphs
• Neural Sketch Learning for Conditional Program Generation
• Inducing Probabilistic Programs by Bayesian Program Merging

Cited by in corpus (10)

• Computer-Aided Design as Language
• 'CADSketchNet' -- An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networks
• Reconstructing editable prismatic CAD from rounded voxel models
• SketchGen: Generating Constrained CAD Sketches
• OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Design
• Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences
• AutoMate: A Dataset and Learning Approach for Automatic Mating of CAD Assemblies
• Parametric Primitive Analysis of CAD Sketches with Vision Transformer
• Vitruvion: A Generative Model of Parametric CAD Sketches
• Engineering Sketch Generation for Computer-Aided Design