Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yihan Hou, Manling Yang, Hao Cui, Lei Wang, Jie Xu, Wei Zeng

TL;DR

Interior color design is a creative task often misaligned by end-to-end AI methods. We introduce C2Ideas, an intent-aligned, domain-aware LLM workflow with three stages—Idea Prompting, Word-Color Association, and Interior Coloring—augmented by an interactive interface and VR visualization. Through formative studies, designer interviews, and user/expert evaluations, C2Ideas demonstrates improved reasonableness, diversity, and controllability compared with baselines lacking domain knowledge. The work highlights how structured prompting and domain knowledge integration can empower designers, offering a practical tool that balances creativity and design rationality in professional practice.

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.

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

TL;DR

Interior color design is a creative task often misaligned by end-to-end AI methods. We introduce C2Ideas, an intent-aligned, domain-aware LLM workflow with three stages—Idea Prompting, Word-Color Association, and Interior Coloring—augmented by an interactive interface and VR visualization. Through formative studies, designer interviews, and user/expert evaluations, C2Ideas demonstrates improved reasonableness, diversity, and controllability compared with baselines lacking domain knowledge. The work highlights how structured prompting and domain knowledge integration can empower designers, offering a practical tool that balances creativity and design rationality in professional practice.

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.
Paper Structure (40 sections, 11 figures, 1 table)

This paper contains 40 sections, 11 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Works
  3. Creative Color Design
  4. Human-AI Collaboration for Creative Design
  5. Large Language Model with Domain Knowledge Integration
  6. Formative Study
  7. Color Theory in Interior Design
  8. Color Psychology
  9. Natural Color System (NCS)
  10. Color Composition
  11. Design Practice
  12. Preliminary Study: Human-AI Collaboration in Interior Color Design
  13. Study Design
  14. Findings
  15. System Overview
  16. ...and 25 more sections

Figures (11)

  • Figure 1: Examples of successful interior color design (A) aligned with the intention of creating a "warm living room", and common pitfalls of contextually misaligned color scheme (B), improper color composition ratios (C), and no coherence with the interior elements (D).
  • Figure 2: Interior color design workflow. 1) Concept design step associates design concepts with styles (A) & tones (B). 2) Color composition step decides primary, secondary, and accent colors (C). 3) Spatial matching step assigns colors to interior elements (D).
  • Figure 3: C2Ideas includes three stages: 1) Idea Prompting: Prompts Generation and Prompt Customization; 2) Word-Color Association: Color Scheme Generation and Color Scheme Customization; 3) Interior Coloring: Color Assignment and Result Refinement.
  • Figure 4: Idea prompting stage. (A) the prompt template, (B) an example of the prompt that maps the user's input to the design concepts, considering the domain knowledge of color psychology theory.
  • Figure 5: Word-color association stage. Given a prompt template (A), the LLM for Word-Color Association returns a positive result (B1) with correct reasoning whilst rejecting three negative examples violating color construction theory (B2 - B4).
  • ...and 6 more figures