CodeCAD: A Parametric CAD Dataset for Programmatic 3D Model Generation

Abstract

Generative models have recently made significant progress in generating 3D content from image or text data, yet existing methods mostly rely on implicit or discretized geometric representations that lack parametric structure or design intent. These limitations make them poorly suited for computer-aided design (CAD). In contrast, code-based CAD representations offer parametric structure and a human-readable presentation but remain underexplored due to the scarcity of datasets. We present a dataset of over 95,000 native OpenSCAD models, primarily containing mechanical parts and engineering components, designed specifically for the programmatic generation of 3D models. The dataset consists of user-created OpenSCAD code, featuring both constructive solid geometry and sketch-and-extrude modeling, along with descriptive metadata, rendered images, and detailed license information. A five-stage pipeline ensures syntactic validity, semantic richness, de-duplication, and quality annotations. To test the dataset's potential, we fine-tuned code-generation large language models for text-to-CAD generation. The evaluation results show consistent improvements in compilation validity and geometric distance to ground-truth samples. By releasing this dataset publicly, we aim to open new opportunities for programmatic 3D model generation.