CSE Community Seminar
March 21, 2025, 12-1PM
Conference Room 45-432 in Building 45
Generative models for manufacturable representations
Ferdous Alam
Postdoctoral Associate, Department of Mechanical Engineering, MIT
Abstract:
The creation of manufacturable and editable 3D shapes through Computer-Aided Design (CAD) remains a highly manual and time-consuming task, hampered by the complex topology of boundary representations of 3D solids and unintuitive design tools. While most work in the 3D shape generation community focuses on representations like meshes, voxels, or point clouds, practical engineering applications demand the modifiability and manufacturability of CAD models and the ability for multi-modal conditional CAD model generation. In this talk, I will introduce a multi-modal generative AI method that employs autoregressive transformers with a contrastive learning framework and latent diffusion models to transform image/sketch inputs into parametric CAD command sequences, resulting in editable 3D shape representations. Extensive evaluations demonstrate that GenCAD significantly outperforms existing state-of-the-art methods in terms of the unconditional and conditional generations of CAD models. Additionally, the contrastive learning framework of GenCAD facilitates the retrieval of CAD models using image queries from large CAD databases—a critical challenge within the CAD community. Finally, I will show some emerging techniques to build a foundational model for 3D mechanical shapes.
March 21, 2025, CSE Community Seminar
Ferdous Alam
Postdoctoral Associate
Department of Mechanical Engineering, MIT