Paired depth images enable mold-friendly shape design and optimization
CAST: Cast-Admissible Generative Design and Shape Optimization with Paired Depth Images
Machine Learning
Summary
Designing complex 3D shapes for molding is tricky because some shapes can get stuck due to undercuts. The paper presents a method that turns 3D shapes into two 2D depth images, which ensures the shapes can be removed from a mold properly. They use AI to create new shapes and then improve those shapes by testing how strong and stiff they are. This approach helps designers make shapes that balance material use and strength while fitting mold constraints.
What this means in practice
- •For product designers: Create 3D parts guaranteed to be moldable without undercuts while exploring new shapes generated by AI.
- •For structural engineers: Refine AI-generated shapes by optimizing stiffness and material usage within mold constraints using finite element analysis.
Authors
Jihoon Kim, Yongmin Kwon, Namwoo Kang
Abstract
Deep generative design can produce complex geometries, but unconstrained representations may create undercuts that prevent release from a two-part mold. We present CAST, which reformulates three-dimensional shape generation under a selected mold-opening constraint as a two-dimensional image generation problem using paired top and bottom depth images. Each valid depth pair defines one material interval along a selected mold-opening direction, so reconstructions exclude undercuts in that direction by construction. Diffusion models generate candidate shapes in this representation, and a finite element analysis (FEA) guided optimizer refines the same two boundaries. We evaluate diffusion-based generation with limited training data comprising 211 SimJEB bracket designs. On SimJEB brackets, FEA-guided refinement with a volume penalty reduced compliance in 193 of 200 generated candidates. The median reduction across all candidates was 36.8 percent in the optimization FEA model. Reconstruction of existing brackets revealed a mass--stiffness trade-off: filling occluded regions increased material volume and reduced displacement under the evaluated loads. Paired depth images thus connect generative exploration and structural refinement in a shared design space that preserves the selected pull-direction restriction.