Generative AI in Color-Changing Systems: Re-Programmable 3D Object Textures with Material and Design Constraints

TL;DR

The paper addresses reprogrammable 3D object textures on photochromic materials using generative AI, emphasizing the need for an end-to-end workflow that respects fabrication constraints. It surveys existing digital-gen AI tools and their lack of physical realizability, contextualizing with Style2Fab and Photo-Chromeleon, and identifies material constraints (restricted color space, channel-dependent timing, light-source effects) and design constraints for data-encoded textures. The authors propose approaches to augment AI systems to operate within feasible color spaces, timing budgets, and hardware modalities, enabling rapid exploration of viable, legible, and data-driven textures. This work has practical implications for rapid physical-texture customization and ambient data displays on reprogrammable surfaces.

Abstract

Advances in Generative AI tools have allowed designers to manipulate existing 3D models using text or image-based prompts, enabling creators to explore different design goals. Photochromic color-changing systems, on the other hand, allow for the reprogramming of surface texture of 3D models, enabling easy customization of physical objects and opening up the possibility of using object surfaces for data display. However, existing photochromic systems require the user to manually design the desired texture, inspect the simulation of the pattern on the object, and verify the efficacy of the generated pattern. These manual design, inspection, and verification steps prevent the user from efficiently exploring the design space of possible patterns. Thus, by designing an automated workflow desired for an end-to-end texture application process, we can allow rapid iteration on different practicable patterns. In this workshop paper, we discuss the possibilities of extending generative AI systems, with material and design constraints for reprogrammable surfaces with photochromic materials. By constraining generative AI systems to colors and materials possible to be physically realized with photochromic dyes, we can create tools that would allow users to explore different viable patterns, with text and image-based prompts. We identify two focus areas in this topic: photochromic material constraints and design constraints for data-encoded textures. We highlight the current limitations of using generative AI tools to create viable textures using photochromic material. Finally, we present possible approaches to augment generative AI methods to take into account the photochromic material constraints, allowing for the creation of viable photochromic textures rapidly and easily.