Deep Generative Methods and Tire Architecture Design

TL;DR

This study compares five deep generative models for industrial tire design, evaluating their performance across various design scenarios using geometry-aware metrics, and introduces categorical inpainting for discrete diffusion models.

Contribution

It provides a comprehensive evaluation of generative models for tire architecture design and introduces categorical inpainting for conditional discrete diffusion modeling.

Findings

Diffusion models outperform other generative models overall.

Masking-trained VAE outperforms multimodal VAE on most metrics.

MDM diffusion model excels in-distribution, DDPM generalizes better out-of-distribution.

Abstract

As deep generative models proliferate across the AI landscape, industrial practitioners still face critical yet unanswered questions about which deep generative models best suit complex manufacturing design tasks. This work addresses this question through a complete study of five representative models (Variational Autoencoder, Generative Adversarial Network, multimodal Variational Autoencoder, Denoising Diffusion Probabilistic Model, and Multinomial Diffusion Model) on industrial tire architecture generation. Our evaluation spans three key industrial scenarios: (i) unconditional generation of complete multi-component designs, (ii) component-conditioned generation (reconstructing architectures from partial observations), and (iii) dimension-constrained generation (creating designs that satisfy specific dimensional requirements). To enable discrete diffusion models to handle conditional scenarios, we introduce categorical inpainting, a mask-aware reverse diffusion process that preserves known labels without requiring additional training. Our evaluation employs geometry-aware metrics specifically calibrated for industrial requirements, quantifying spatial coherence, component interaction, structural connectivity, and perceptual fidelity. Our findings reveal that diffusion models achieve the strongest overall performance; a masking-trained VAE nonetheless outperforms the multimodal variant MMVAE\textsuperscript{+} on nearly all component-conditioned metrics, and within the diffusion family MDM leads in-distribution whereas DDPM generalises better to out-of-distribution dimensional constraints.