131. AI and Interactive Tools for the Arts
発表担当
目次
説明
Museums aim at personalizing visits to offer tailored content and encourage visitors to come back. Unfortunately, museum professionals find it difficult to reflect on the vast number of visitor profiles when creating personalized visits. We propose Museo* a new concept to support their creation strategy by allowing the selection of visitor characteristics. Through an interactive design process, we instantiated this concept with MuseoTUI, that displays the progress of visit creation by illuminating physical tokens, and MuseoGUI that displays on a standard touchscreen. In an in-situ comparative structured observation, we evaluated both prototypes. The concept Museo* is well understood and accepted with both interaction styles. MuseoGUI was perceived as more efficient, while MuseoTUI provided better stimulation, higher user experience and the physical manipulation was described as a valuable support for empathy, reflection, and creation. Based on these findings, we present design implications for future systems supporting the creation of personalized visits.
日本語まとめ
説明
Ink painting, renowned for its aesthetics and historical significance, plays a vital role in global art. 3D ink art extends this tradition into spatial forms, enriching digital media like animation and games. However, existing methods for 3D ink creation demand expertise in both 3D modeling and ink aesthetics, limiting novice participation and 3D ink application.Through formative research with four experts, including ink painting artists and 3D designers, we summarize the core challenge: how to preserve the expressive pattern of ink paintings while constructing 3D structures.To tackle this challenge, we introduce 3DInkGen, a system that transforms 2D ink elements into editable 3D compositions. 3DInkGen follows a four-stage workflow: element extraction, form generation, 3D reconstruction, and style transfer.A user study with sixteen novices showed 3DInkGen lowers technical barriers and enables intuitive 3D composition. The four experts believe novice-created works captured the artistic style of ink painting while maintain 3D structure of elements.
日本語まとめ
説明
Large Language Models (LLMs) hold promise in supporting creative writing, yet the role of proactive AI in collaborative writing remains underexplored due to concerns around human agency and disruption. To investigate effective strategies for proactive AI support, we conducted a Wizard-of-Oz study simulating two suggestion styles: intrusive suggestions (next-sentence completions) and non-intrusive suggestions (exploratory proposals), where participants completed two story outlining tasks under each style, receiving real-time proactive suggestions from a human wizard acting as the AI. Both quantitative and qualitative results show that proactive AI can enhance creativity and accelerate writing. However, we observed a trade-off between AI involvement and perceived human agency. This trade-off was moderated by how strongly AI stimulated users—greater inspiration led to stronger perceived agency even under high AI involvement. Based on wizards' behavior, we offer guidance on suggestion style and timing to better balance creativity and agency for future proactive AI writing systems.
日本語まとめ
説明
Current AI writing tools aim to enhance authorial capacity yet often diminish authorial control and lack timely audience feedback. Through a formative study with fiction authors (N=10), we uncovered two critical tensions in human–AI co-writing: balancing AI scaffolding with authorial ownership, and the absence of contextual audience perspectives that shape storytelling during drafting. Guided by these insights, we designed Plotania, a co-writing system that combines proactive virtual readers offering real-time audience reactions with transparent attribution layers. A controlled study (N=20) revealed complex and counterintuitive effects: virtual reader feedback increased audience awareness but decreased perceived creative agency, transforming individual authorship into collaborative performance. Transparent attribution raised awareness of AI contributions but triggered identity anxiety and reduced AI usage. These findings reveal fundamental trade-offs in transparency design. We contribute design principles for "agency-preserving transparency" that balance information provision with creative empowerment, informing future transparency design in human-AI creative collaboration.
日本語まとめ
説明
In science fiction writing, ideation demands both novelty to construct fictional worlds and consistency to maintain internal and temporal logic within those worlds. While large language models (LLMs) are increasingly adopted as co-creators, generated ideas often lack surprise and struggle to maintain consistency. Moreover, current interaction paradigms of human-AI co-creation systems fail to support the fragmented and iterative nature of science fiction ideation. To address these challenges, we introduce Sci-Fi Spark, a human-AI co-creation system to support inspiration and organization in the ideation phase. The system features an Ideation Canvas for visualizing relationships between fragmented ideas, a Novelty Generator that applies computational creativity strategies to produce novel worldbuilding inspirations, and a Consistency Generator to produce context-aware storyline suggestions. A technical evaluation and a user study with writers show that Sci-Fi Spark enhances both novelty and consistency, while enabling iterative co-ideation with LLMs.
日本語まとめ
説明
We present a participatory co-design cycle that studied synaesthesia, a cross-sensory phenomenon where one stimulus automatically triggers another perception. We worked with a community of synaesthetes to develop and evaluate an interactive technology to depict and communicate synaesthetic experience. By working with qualitative methods to understand experience, we accommodate the highly individual nature and support otherwise limited sensory vocabulary and lack of shared understanding of the condition. The first study involved a series of participatory workshops that explored text, creative tools, interactive technologies, and sensory materials in conveying the synaesthetic experience. Insights from these workshops informed the development of the Somatic Drawing Tool that allows users to depict their experiences. Within the tool, we deployed the 3D Body Sheet, an immersive extension of techniques drawn from soma design. We engaged users in an initial evaluation of the system and took on board their feedback in a subsequent cycle of iterative development. This resulted in a bespoke system that could be personalised to diverse types of individual synaesthetic experience. This enables nuanced articulation, providing a supportive environment for externalising and reflecting sensations.
日本語まとめ
説明
The “Ideorealm Alignment of Paintings and Poems (IA-PP)” theory rooted in Chinese classical aesthetics offers a perspective for exploring poetry’s deep connotations. This study presents PoemPalette, a novel IA-PP creative-exploration tool that integrates generative AI to guide poetry enthusiasts in actively constructing an ideorealm for the poetic painting they envision, informed by a formative study with six experts. We extract the core symbols of poetry, transform them into Scene Graph (SG), and generate images for users to freely compose, enabling IA-PP creative exploration. The system incorporates Large Language Model (LLM) agents to enhance the foundational understanding of poetry. In a controlled experiment on Chinese poetry and Japanese haiku with 60 participants, we analyze which interaction mechanisms most contribute to foundational understanding and creative outcomes, compared with both AI and non-AI baselines. Situated within East Asian poetry traditions, this study introduces cultural theories to guide the design of AI co-creation tools, using a graph-based interface of interpretable intermediate representations.