EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation

Anna C. Doris, Ferdous Alam, Amin Heyrani Nobari, Faez Ahmed

Journal of Mechanical Design · 01.07.2026 · 148 (7)

DOI: 10.1115/1.4071305 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Mechanical Design, online erschienen am 23.03.2026. Verfasst von Anna C. Doris und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Division of Graduate Education, International Business Machines Corporation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Efficient creation of accurate and editable 3D CAD models is critical in engineering design, significantly impacting cost and time to market in product innovation. Current manual workflows remain highly time consuming and demand extensive user expertise. While recent developments in AI-driven CAD generation show promise, existing approaches are often constrained by limited CAD representations, inability to generalize to real-world images, or low output accuracy due to a lack of domain-specific knowledge. To address these challenges, this article introduces CAD-Coder, an open-source vision-language model (VLM) explicitly fine-tuned to generate editable CAD code (CadQuery Python) directly from visual input. Leveraging a large-scale dataset that we constructed—GenCAD-Code, consisting of over 163k CAD model image and code pairs—CAD-Coder outperforms VLM baselines such as GPT-4.5 and Qwen2.5-VL-72B on image-conditioned CAD code generation, achieving a 100% valid syntax rate and the highest accuracy in 3D solid similarity. Notably, our VLM exhibits initial signs of generalizability, generating CAD code from real-world images and utilizing a CAD operation not explicitly seen during fine-tuning. The performance and adaptability of CAD-Coder highlight the potential of VLMs fine-tuned on code to streamline CAD workflows for engineers and designers. CAD-Coder is publicly available.

Förderung

  • Division of Graduate Education
  • International Business Machines Corporation

Zitieren

APA

Doris, A. C., Alam, F., Nobari, A. H., & Ahmed, F. (2026). CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation. Journal of Mechanical Design, 148(7). https://doi.org/10.1115/1.4071305

Vancouver

Doris AC, Alam F, Nobari AH, Ahmed F. CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation. Journal of Mechanical Design. 2026;148(7). doi:10.1115/1.4071305

BibTeX
@article{Doris2026,
  author = {Doris, Anna C. and Alam, Ferdous and Nobari, Amin Heyrani and Ahmed, Faez},
  title = {CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation},
  journal = {Journal of Mechanical Design},
  year = {2026},
  volume = {148},
  number = {7},
  doi = {10.1115/1.4071305}
}
Kostenlos starten →