C2Ideas: Supporting Creative Interior Color Design Ideation with Large Language Model

Abstract

Interior color design is a creative process that endeavors to allocate colors to furniture and other elements within an interior space. While much research focuses on generating realistic interior designs, these automated approaches often misalign with user intention and disregard design rationales. Informed by a need-finding preliminary study, we develop C2Ideas, an innovative system for designers to creatively ideate color schemes enabled by an intent-aligned and domain-oriented large language model. C2Ideas integrates a three-stage process: Idea Prompting stage distills user intentions into color linguistic prompts; Word-Color Association stage transforms the prompts into semantically and stylistically coherent color schemes; and Interior Coloring stage assigns colors to interior elements complying with design principles. We also develop an interactive interface that enables flexible user refinement and interpretable reasoning. C2Ideas has undergone a series of indoor cases and user studies, demonstrating its effectiveness and high recognition of interactive functionality by designers.

26 pages, 11 figures

References in corpus (7)

• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
• Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback
• How Do UX Practitioners Communicate AI as a Design Material? Artifacts, Conceptions, and Propositions
• Learning Personal Style from Few Examples
• Methods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey
• CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis

Cited by in corpus (6)

• AIdeation: Designing a Human-AI Collaborative Ideation System for Concept Designers
• Inkspire: Supporting Design Exploration with Generative AI through Analogical Sketching
• HarmonyCut: Supporting Creative Chinese Paper-cutting Design with Form and Connotation Harmony
• DesignFromX: Empowering Consumer-Driven Design Space Exploration through Feature Composition of Referenced Products
• Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation
• Exploring the Innovation Opportunities for Pre-trained Models