Adversarial Latent Autoencoder with Self-Attention for Structural Image Synthesis

TL;DR

This paper introduces SA-ALAE, a novel generative model that leverages self-attention and adversarial autoencoding to produce structurally rich engineering design images, enabling controlled exploration of design variants.

Contribution

The paper presents SA-ALAE, a new model combining self-attention with adversarial autoencoders to generate and control complex engineering design images, addressing limitations of convolutional DGMs.

Findings

Successfully generated engineering blueprints for automotive parts.

Enabled controlled exploration of design variants.

Demonstrated effectiveness on real industrial design tasks.

Abstract

Generative Engineering Design approaches driven by Deep Generative Models (DGM) have been proposed to facilitate industrial engineering processes. In such processes, designs often come in the form of images, such as blueprints, engineering drawings, and CAD models depending on the level of detail. DGMs have been successfully employed for synthesis of natural images, e.g., displaying animals, human faces and landscapes. However, industrial design images are fundamentally different from natural scenes in that they contain rich structural patterns and long-range dependencies, which are challenging for convolution-based DGMs to generate. Moreover, DGM-driven generation process is typically triggered based on random noisy inputs, which outputs unpredictable samples and thus cannot perform an efficient industrial design exploration. We tackle these challenges by proposing a novel model Self-Attention Adversarial Latent Autoencoder (SA-ALAE), which allows generating feasible design images of complex engineering parts. With SA-ALAE, users can not only explore novel variants of an existing design, but also control the generation process by operating in latent space. The potential of SA-ALAE is shown by generating engineering blueprints in a real automotive design task.