Text2CSG: Generating CAD models from natural language via constructive solid geometry

Lupeng Zhang

doi:10.1016/j.cad.2026.104127

Text2CSG: Generating CAD models from natural language via constructive solid geometry

2026-07-01

0

PRE

AI

DOI：10.1016/j.cad.2026.104127

Original

Original request for help

Save

Abstract

En 中文

Computer-aided design (CAD) plays a central role in engineering, manufacturing, and 3D content creation, but producing precise CAD models directly from natural language is still difficult. We propose Text2CSG, a two-stage framework for producing high-quality CAD models from text. Our approach uses Constructive Solid Geometry (CSG) as an intermediate representation to capture the structured and hierarchical nature of CAD construction. Unlike prior approaches based on sketch-extrusion sequences, Text2CSG exploits the Boolean compositional logic of CSG trees to represent complex shapes. The system consists of two primary components: (1) a geometry decoder that reconstructs 3D shapes from CSG programs, and (2) a structure-aware Transformer conditioned on high-level semantics extracted from a frozen large language model (LLM). By decoupling semantic understanding from geometric generation, our approach benefits from pre-trained LLMs without requiring fine-tuning. Experiments on a newly constructed CSG dataset demonstrate that Text2CSG achieves higher geometric accuracy and stronger structural consistency than existing methods. Furthermore, the utilization of structured CSG programs makes the generation process interpretable and editable, enabling flexible text-driven CAD design. We will release the source code and dataset.

Keywords:

Constructive solid geometry

CAD models

3D generation

Large language models

Text2CSG: Generating CAD models from natural language via constructive solid geometry

Abstract

Journal

Organization

Cited Papers