GenCAD-Three-Dimensional: Computer-Aided Design Program Generation Using Multimodal Latent Space Alignment and Synthetic Dataset Balancing
Name
md-25-1380.pdf
Description
Published version
Size
1.45 MB
Format
Adobe PDF
Checksum (MD5)
2ece02628e08d7ed4f7d5154029bc097
Author(s)
Yu, Nomi
Ferdous Alam, Md
Hart, A John
Ahmed, Faez
Date Issued
September 23, 2025
Journal
Journal of Mechanical Design
Publisher
ASME International
Citation
Yu, N., Ferdous Alam, M., Hart, A. J., and Ahmed, F. (September 23, 2025). "GenCAD-Three-Dimensional: Computer-Aided Design Program Generation Using Multimodal Latent Space Alignment and Synthetic Dataset Balancing." ASME. J. Mech. Des. March 2026; 148(3): 031703.
Version
Final published version
Abstract
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.
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1115/1.4069276
