Computer-Aided Design as Language

Abstract

Computer-Aided Design (CAD) applications are used in manufacturing to model everything from coffee mugs to sports cars. These programs are complex and require years of training and experience to master. A component of all CAD models particularly difficult to make are the highly structured 2D sketches that lie at the heart of every 3D construction. In this work, we propose a machine learning model capable of automatically generating such sketches. Through this, we pave the way for developing intelligent tools that would help engineers create better designs with less effort. Our method is a combination of a general-purpose language modeling technique alongside an off-the-shelf data serialization protocol. We show that our approach has enough flexibility to accommodate the complexity of the domain and performs well for both unconditional synthesis and image-to-sketch translation.

arXiv comment24 pages, 11 figures, 3 tables

References in corpus (15)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Auto-Encoding Variational Bayes
• Neural Message Passing for Quantum Chemistry
• Language Models are Few-Shot Learners
• Conditional Image Generation with PixelCNN Decoders
• Zero-Shot Text-to-Image Generation
• The Curious Case of Neural Text Degeneration
• A Neural Representation of Sketch Drawings
• Synthesizing Programs for Images using Reinforced Adversarial Learning
• Jukebox: A Generative Model for Music
• Deep Vectorization of Technical Drawings
• PolyGen: An Autoregressive Generative Model of 3D Meshes
• SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design
• DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
• Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences

Cited by in corpus (6)

• Reconstructing editable prismatic CAD from rounded voxel models
• SketchGen: Generating Constrained CAD Sketches
• OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Design
• A Survey of Methods for Converting Unstructured Data to CSG Models
• Vitruvion: A Generative Model of Parametric CAD Sketches
• Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface