Computer-Aided Design as Language

TL;DR

This paper introduces a machine learning model that automatically generates structured 2D sketches in CAD, aiming to assist engineers and streamline the design process.

Contribution

It combines language modeling with data serialization to create a flexible system capable of unconditional sketch synthesis and image-to-sketch translation.

Findings

Effective in generating complex CAD sketches

Performs well in both unconditional and image-to-sketch tasks

Lays groundwork for intelligent CAD design tools

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.