Zero-shot CAD Program Re-Parameterization for Interactive Manipulation

TL;DR

This paper presents a zero-shot method that uses pre-trained language and image models to infer meaningful shape variations and re-parameterize CAD models, facilitating easier and more intuitive design exploration.

Contribution

It introduces a novel zero-shot pipeline that captures design semantics and constraints from pre-trained models to re-parameterize CAD programs without additional training.

Findings

Enables intuitive shape manipulation through semantic re-parameterization.

Successfully captures meaningful design variations without task-specific training.

Facilitates effortless exploration of design space along meaningful axes.

Abstract

Parametric CAD models encode entire families of shapes that should, in principle, be easy for designers to explore. However, in practice, parametric CAD models can be difficult to manipulate due to implicit semantic constraints among parameter values. Finding and enforcing these semantic constraints solely from geometry or programmatic shape representations is not possible because these constraints ultimately reflect design intent. They are informed by the designer's experience and semantics in the real world. To address this challenge, we introduce a zero-shot pipeline that leverages pre-trained large language and image model to infer meaningful space of variations for a shape. We then re-parameterize a new constrained parametric CAD program that captures these variations, enabling effortless exploration of the design space along meaningful design axes.