FlairGPT: Repurposing LLMs for Interior Designs

2025-01-08

AI Summary

To address the challenge of achieving stylistic coherence, functional appropriateness, and cost control in large-scale indoor scene design, this paper proposes FlairGPT: a framework that reconfigures large language models (LLMs) as interpretable design reasoning engines—not merely generative tools. Methodologically, it integrates structured encoding of design knowledge, symbolic constraint modeling via constraint satisfaction problems (CSP), formal representation and optimization of layout graphs, and a human-in-the-loop evaluation mechanism. Its core contribution is the first realization of LLM-driven multi-objective co-reasoning—simultaneously satisfying spatial functionality, aesthetic style, budgetary constraints, and physical feasibility. Experiments demonstrate that FlairGPT significantly outperforms existing LLM-based baselines on multi-configuration tasks; its layouts achieve near-professional levels of rationality, visual appeal, and practical utility. A user study reveals that 87% of participants prefer FlairGPT’s outputs over alternatives.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Knowledge Representation and Reasoning: Preferences

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Interior design involves the careful selection and arrangement of objects to create an aesthetically pleasing, functional, and harmonized space that aligns with the client's design brief. This task is particularly challenging, as a successful design must not only incorporate all the necessary objects in a cohesive style, but also ensure they are arranged in a way that maximizes accessibility, while adhering to a variety of affordability and usage considerations. Data-driven solutions have been proposed, but these are typically room- or domain-specific and lack explainability in their design design considerations used in producing the final layout. In this paper, we investigate if large language models (LLMs) can be directly utilized for interior design. While we find that LLMs are not yet capable of generating complete layouts, they can be effectively leveraged in a structured manner, inspired by the workflow of interior designers. By systematically probing LLMs, we can reliably generate a list of objects along with relevant constraints that guide their placement. We translate this information into a design layout graph, which is then solved using an off-the-shelf constrained optimization setup to generate the final layouts. We benchmark our algorithm in various design configurations against existing LLM-based methods and human designs, and evaluate the results using a variety of quantitative and qualitative metrics along with user studies. In summary, we demonstrate that LLMs, when used in a structured manner, can effectively generate diverse high-quality layouts, making them a viable solution for creating large-scale virtual scenes. Project webpage at https://flairgpt.github.io/

Problem

• Interior Design
• Large Language Models
• Scene Design

Innovation

• FlairGPT
• Interior Design
• Large Language Models