[Paper Review] InkIdeator: Supporting Chinese-Style Visual Design Ideation via AI-Infused Exploration of Chinese Paintings

Shiwei Wu, Ziyao Gao+7 more|arXiv (Cornell University)|Jan 26, 2026

Aesthetic Perception and Analysis0 citations

TL;DR

InkIdeator is an AI-assisted ideation tool that annotates Chinese paintings along cultural symbols, emotions, compositions, and styles to aid Chinese-style visual design ideation, validated by formative and within-subjects studies.

ABSTRACT

Visual designers often seek inspiration from Chinese paintings when tasked with creating Chinese-style illustrations, posters, etc. Our formative study (N=10) reveals that during ideation, designers learn the cultural symbols, emotions, compositions, and styles in Chinese paintings but face challenges in searching, analyzing, and integrating these dimensions. This paper leverages multi-modal large models to annotate the value of each dimension in 16,315 Chinese paintings, built on which we propose InkIdeator, an ideation support system for Chinese-style visual designs. InkIdeator suggests cultural symbols associated with the task theme, provides dimensional keywords to help analyze Chinese paintings, and generates visual examples integrating user-selected keywords. Our within-subjects study (N=12) using a baseline system without extracted dimensional keywords, along with two extended use cases by Chinese painters, indicates InkIdeator's effectiveness in creative ideation support, helping users efficiently explore cultural dimensions in Chinese paintings and visualize their ideas. We discuss implications for supporting culture-related visual design ideation with generative AI.

Motivation & Objective

• Identify design challenges designers face when ideating with Chinese paintings.
• Create a richly annotated Chinese painting dataset capturing cultural symbols, emotions, compositions, and styles.
• Develop InkIdeator to help search, analyze, and visualize design elements from paintings for ideation.

Proposed method

• Conduct a formative study with 10 designers to identify ideation challenges and preferred dimensions in Chinese paintings.
• Build a dataset of 16,315 Chinese paintings annotated with cultural symbols, emotions, dimensions, and styles using a multimodal LLM (GPT-4o mini) prompted with Role Play, Dimension Analysis, Knowledge Injection and JSON outputs.
• Annotate and cluster cultural symbols and emotions; classify painting types (Gongbi/Xieyi) with a classifier trained on 500 images.
• Develop four interactive components (Symbol Association Panel, Image Library, Moodboard Canvas, Image Generation Panel) linked to the annotated dataset to support three iterative tasks: Search Reference, Analyze Reference, Visualize Ideas.
• Evaluate InkIdeator with a within-subjects study (N=12) against a baseline (ChatGPT + image search + MidJourney) and two case studies with Chinese painters.

Experimental results

Research questions

• RQ1 How can AI annotate and organize cultural symbols, emotions, compositions, and styles from Chinese paintings to support design ideation?
• RQ2 Does InkIdeator improve designers' ability to search, analyze, and visualize Chinese-style visual design references compared with a baseline?
• RQ3 Can experienced Chinese painters effectively use InkIdeator for ideation tasks beyond designers?
• RQ4 What design space and workflow considerations arise when integrating generative AI into culture-specific ideation processes?

Key findings

• InkIdeator enabled organized exploration of visual references and more efficient extraction of design elements from Chinese paintings.
• Participants perceived InkIdeator as providing greater creative support than the baseline in ideation tasks.
• The tool facilitated turning ideas into visual representations more efficiently than the baseline.
• Two experienced Chinese painters successfully iterated on ideas with InkIdeator, suggesting potential generalization to culture-related creative tasks.
• An annotated design space derived from 16,315 paintings covers cultural symbols, emotions, compositions, and styles guiding search and analysis.