EUVIMEDEUVIMED entdecken
Crossref

GenCAD-Three-Dimensional: Computer-Aided Design Program Generation Using Multimodal Latent Space Alignment and Synthetic Dataset Balancing

Nomi Yu, Md Ferdous Alam, A. John Hart, Faez Ahmed

Journal of Mechanical Design · 01.03.2026 · 148 (3)

DOI: 10.1115/1.4069276 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Mechanical Design, online erschienen am 23.09.2025. Verfasst von Nomi Yu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 57 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computer-aided design (CAD) programs, structured as parametric sequences of commands that compile into precise 3D geometries, are fundamental to accurate and efficient engineering design processes. Generating these programs from nonparametric data such as point clouds and meshes remains a crucial yet challenging task, typically requiring extensive manual intervention. Current deep generative models aimed at automating CAD generation are significantly limited by imbalanced and insufficiently large datasets, particularly those lacking representation for complex CAD programs. To address this, we introduce GenCAD-3D, a multimodal generative framework utilizing contrastive learning for aligning latent embeddings between CAD and geometric encoders, combined with latent diffusion models for CAD sequence generation and retrieval. In addition, we present SynthBal, a synthetic data augmentation strategy specifically designed to balance and expand datasets, notably enhancing representation of complex CAD geometries. Our experiments show that SynthBal significantly boosts reconstruction accuracy, reduces the generation of invalid CAD models, and markedly improves performance on high-complexity geometries, surpassing existing benchmarks. These advancements hold substantial implications for streamlining reverse engineering and enhancing automation in engineering design. We will publicly release our datasets and code, including a set of 51 3D-printed and laser-scanned parts on our project site.

Zitieren

APA

Yu, N., Alam, M. F., Hart, A. J., & Ahmed, F. (2026). GenCAD-Three-Dimensional: Computer-Aided Design Program Generation Using Multimodal Latent Space Alignment and Synthetic Dataset Balancing. Journal of Mechanical Design, 148(3). https://doi.org/10.1115/1.4069276

Vancouver

Yu N, Alam MF, Hart AJ, Ahmed F. GenCAD-Three-Dimensional: Computer-Aided Design Program Generation Using Multimodal Latent Space Alignment and Synthetic Dataset Balancing. Journal of Mechanical Design. 2026;148(3). doi:10.1115/1.4069276

BibTeX
@article{Yu2026,
  author = {Yu, Nomi and Alam, Md Ferdous and Hart, A. John and Ahmed, Faez},
  title = {GenCAD-Three-Dimensional: Computer-Aided Design Program Generation Using Multimodal Latent Space Alignment and Synthetic Dataset Balancing},
  journal = {Journal of Mechanical Design},
  year = {2026},
  volume = {148},
  number = {3},
  doi = {10.1115/1.4069276}
}
Kostenlos starten →