Computational study demonstrates automated parametric modeling from 3-D scans for customized wearables, indicating improved geometric fidelity and manufacturing efficiency.
Key Points
To develop and evaluate an automated design framework that translates unstructured 3-D scan data into constraint-satisfying, manufacturable parametric CAD models for customized wearables.
Integrated machine learning algorithms for image-to-point cloud conversion and point cloud-to-surface reconstruction.
Coupled data-driven surface reconstruction with constraint-aware generative modeling to generate solid CAD models for additive manufacturing.
Evaluated analytical and hybrid reconstruction methods using curvature-derived smoothness and manufacturability metrics across an anatomical case study.
Constraint integration improved geometric fidelity and design efficiency when translating irregular 3-D scan geometries into solid CAD models.
Hybrid reconstruction approaches achieved superior surface smoothness and manufacturability metrics compared to analytical methods.