CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generation

TL;DR

This paper introduces CAD-Llama, a framework that adapts large language models to generate parametric 3D CAD models by translating commands into structured code and fine-tuning with CAD-specific data, achieving superior results.

Contribution

CAD-Llama presents a novel hierarchical annotation pipeline and an adaptive pretraining approach to enable LLMs to generate 3D CAD parametric sequences effectively.

Findings

Outperforms prior autoregressive methods

Significantly improves generation accuracy

Enhances LLM understanding of 3D parametric sequences

Abstract

Recently, Large Language Models (LLMs) have achieved significant success, prompting increased interest in expanding their generative capabilities beyond general text into domain-specific areas. This study investigates the generation of parametric sequences for computer-aided design (CAD) models using LLMs. This endeavor represents an initial step towards creating parametric 3D shapes with LLMs, as CAD model parameters directly correlate with shapes in three-dimensional space. Despite the formidable generative capacities of LLMs, this task remains challenging, as these models neither encounter parametric sequences during their pretraining phase nor possess direct awareness of 3D structures. To address this, we present CAD-Llama, a framework designed to enhance pretrained LLMs for generating parametric 3D CAD models. Specifically, we develop a hierarchical annotation pipeline and a code-like format to translate parametric 3D CAD command sequences into Structured Parametric CAD Code (SPCC), incorporating hierarchical semantic descriptions. Furthermore, we propose an adaptive pretraining approach utilizing SPCC, followed by an instruction tuning process aligned with CAD-specific guidelines. This methodology aims to equip LLMs with the spatial knowledge inherent in parametric sequences. Experimental results demonstrate that our framework significantly outperforms prior autoregressive methods and existing LLM baselines.