B\'ezierGAN: Automatic Generation of Smooth Curves from Interpretable Low-Dimensional Parameters

TL;DR

BézierGAN is a deep learning model that generates smooth, realistic curves from low-dimensional parameters, aiding design optimization in aerospace and ship industries.

Contribution

It introduces a novel generative model that maps low-dimensional latent vectors to rational Bézier curves, enabling smooth curve synthesis and shape variation control.

Findings

Generates diverse, realistic curves

Preserves shape variation in latent space

Effective in synthetic and real-world tasks

Abstract

Many real-world objects are designed by smooth curves, especially in the domain of aerospace and ship, where aerodynamic shapes (e.g., airfoils) and hydrodynamic shapes (e.g., hulls) are designed. To facilitate the design process of those objects, we propose a deep learning based generative model that can synthesize smooth curves. The model maps a low-dimensional latent representation to a sequence of discrete points sampled from a rational B\'ezier curve. We demonstrate the performance of our method in completing both synthetic and real-world generative tasks. Results show that our method can generate diverse and realistic curves, while preserving consistent shape variation in the latent space, which is favorable for latent space design optimization or design space exploration.