Draw it like Euclid: Teaching transformer models to generate CAD profiles using ruler and compass construction steps

TL;DR

This paper presents a method for generating CAD profiles through geometric construction sequences, improving quality and enabling parametric editing, with reinforcement learning further enhancing the results.

Contribution

It introduces a novel approach combining geometric construction sequences with reinforcement learning to generate and refine CAD profiles from designer input.

Findings

Construction sequences improve generation quality.

Reinforcement learning enhances results beyond explicit metrics.

Parametric editing is enabled with high precision.

Abstract

We introduce a new method of generating Computer Aided Design (CAD) profiles via a sequence of simple geometric constructions including curve offsetting, rotations and intersections. These sequences start with geometry provided by a designer and build up the points and curves of the final profile step by step. We demonstrate that adding construction steps between the designer's input geometry and the final profile improves generation quality in a similar way to the introduction of a chain of thought in language models. Similar to the constraints in a parametric CAD model, the construction sequences reduce the degrees of freedom in the modeled shape to a small set of parameter values which can be adjusted by the designer, allowing parametric editing with the constructed geometry evaluated to floating point precision. In addition we show that applying reinforcement learning to the construction sequences gives further improvements over a wide range of metrics, including some which were not explicitly optimized.