Stylish and Functional: Guided Interpolation Subject to Physical Constraints

TL;DR

This paper introduces a zero-shot diffusion-based framework that enforces physical constraints, like rotational symmetry, during design generation, improving realism and functional compliance in AI-generated engineering designs.

Contribution

It proposes a novel method to incorporate physical constraints into generative AI models without additional training, demonstrated through symmetry-guided wheel design generation.

Findings

Generated designs have higher realism (lower FID scores).

Designs more closely satisfy physical constraints with the proposed guidance.

Method outperforms related approaches in producing physically compliant designs.

Abstract

Generative AI is revolutionizing engineering design practices by enabling rapid prototyping and manipulation of designs. One example of design manipulation involves taking two reference design images and using them as prompts to generate a design image that combines aspects of both. Real engineering designs have physical constraints and functional requirements in addition to aesthetic design considerations. Internet-scale foundation models commonly used for image generation, however, are unable to take these physical constraints and functional requirements into consideration as part of the generation process. We consider the problem of generating a design inspired by two input designs, and propose a zero-shot framework toward enforcing physical, functional requirements over the generation process by leveraging a pretrained diffusion model as the backbone. As a case study, we consider the example of rotational symmetry in generation of wheel designs. Automotive wheels are required to be rotationally symmetric for physical stability. We formulate the requirement of rotational symmetry by the use of a symmetrizer, and we use this symmetrizer to guide the diffusion process towards symmetric wheel generations. Our experimental results find that the proposed approach makes generated interpolations with higher realism than methods in related work, as evaluated by Fr\'echet inception distance (FID). We also find that our approach generates designs that more closely satisfy physical and functional requirements than generating without the symmetry guidance.