Three-dimensional Deep Shape Optimization with a Limited Dataset

TL;DR

This paper introduces a deep learning framework for 3D shape optimization that performs well with limited datasets by using positional encoding and Lipschitz regularization, enabling practical design improvements.

Contribution

It presents a novel shape optimization method that effectively handles small datasets, improving robustness and generalizability in 3D design tasks.

Findings

Demonstrates robustness and effectiveness on diverse 3D datasets

Achieves high-quality shape optimization results with limited data

Shows versatility across different object types like wheels and cars

Abstract

Generative models have attracted considerable attention for their ability to produce novel shapes. However, their application in mechanical design remains constrained due to the limited size and variability of available datasets. This study proposes a deep learning-based optimization framework specifically tailored for shape optimization with limited datasets, leveraging positional encoding and a Lipschitz regularization term to robustly learn geometric characteristics and maintain a meaningful latent space. Through extensive experiments, the proposed approach demonstrates robustness, generalizability and effectiveness in addressing typical limitations of conventional optimization frameworks. The validity of the methodology is confirmed through multi-objective shape optimization experiments conducted on diverse three-dimensional datasets, including wheels and cars, highlighting the model's versatility in producing practical and high-quality design outcomes even under data-constrained conditions.