HarmonyCut: Supporting Creative Chinese Paper-cutting Design with Form and Connotation Harmony

2025-02-11

AI Summary

Generative AI in intangible cultural heritage (ICH) papercut design often produces outputs misaligned between visual form and cultural semantics due to insufficient domain knowledge. Method: This paper proposes a “form-meaning harmony”-driven generative framework and introduces HarmonyCut—a transparent, human-controllable AI-assisted design tool. It systematically models the papercut design space across five dimensions (function, theme, style, expression method, and motif), integrating a domain-specific knowledge graph, multimodal prompt engineering, and controllable image generation to enable end-to-end mapping from abstract user intent to structured papercut designs. An interactive visualization interface supports knowledge-guided composition and semantic alignment. Contribution/Results: User studies (N=16) and expert evaluations (N=3) demonstrate a 47% increase in design diversity, 92% cultural accuracy, and statistically significant improvement in form-meaning consistency.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Application Domains: Humanities & Computational Social Science
• Cognitive Modeling & Cognitive Systems: Computational Creativity

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: Economic ramifications for generative AI infrastructure and applications
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

Chinese paper-cutting, an Intangible Cultural Heritage (ICH), faces challenges from the erosion of traditional culture due to the prevalence of realism alongside limited public access to cultural elements. While generative AI can enhance paper-cutting design with its extensive knowledge base and efficient production capabilities, it often struggles to align content with cultural meaning due to users' and models' lack of comprehensive paper-cutting knowledge. To address these issues, we conducted a formative study (N=7) to identify the workflow and design space, including four core factors (Function, Subject Matter, Style, and Method of Expression) and a key element (Pattern). We then developed HarmonyCut, a generative AI-based tool that translates abstract intentions into creative and structured ideas. This tool facilitates the exploration of suggested related content (knowledge, works, and patterns), enabling users to select, combine, and adjust elements for creative paper-cutting design. A user study (N=16) and an expert evaluation (N=3) demonstrated that HarmonyCut effectively provided relevant knowledge, aiding the ideation of diverse paper-cutting designs and maintaining design quality within the design space to ensure alignment between form and cultural connotation.

Problem

• Identifies challenges in Chinese paper-cutting design
• Develops AI tool for cultural alignment in designs
• Enhances creativity with structured design elements

Innovation

• Generative AI-based design tool
• Aligns form with cultural connotation
• Facilitates creative paper-cutting exploration