TraitSpaces：迈向人机共创的可解释视觉创造力
TraitSpaces: Towards Interpretable Visual Creativity for Human-AI Co-Creation
AI总结：
本文提出TraitSpaces框架，基于心理学与艺术家访谈定义12项视觉创造力特质，并用SemArt和GPT 4.1标注、CLIP评估其可学习性，以可解释特质空间支持人机共创。
摘要：
我们提出了一个基于心理学并吸纳艺术家见解的框架，用于对四个领域的视觉创造力进行建模：内在世界、外在世界、想象世界和道德世界。借助对执业艺术家的访谈以及心理学理论，我们定义了12项特质，用以捕捉创造力的情感、象征、文化和伦理维度。我们使用SemArt数据集中的2万件艺术品，通过GPT 4.1依据详尽且与理论一致的提示对图像进行标注，并评估从CLIP图像嵌入中学习这些特质的可学习性。Environmental Dialogicity和Redemptive Arc等特质能够以高可靠性被预测（R²约为0.64–0.68），而Memory Imprint等其他特质仍具挑战性，这凸显了纯视觉编码的局限。除技术指标外，我们可视化了一个“创造力特质空间”，并说明它如何支持可解释、具备特质意识的共创——例如沿Redemptive Arc轴滑动，以探索关于逆境与重生的作品。通过将文化—美学洞见与计算建模相连接，我们的工作并非要把创造力简化为数字，而是要为艺术家、研究者和AI系统提供共同语言与可解释工具，以开展有意义的协作。
英文摘要：
We introduce a psychologically grounded and artist-informed framework for modeling visual creativity across four domains: Inner, Outer, Imaginative, and Moral Worlds. Drawing on interviews with practicing artists and theories from psychology, we define 12 traits that capture affective, symbolic, cultural, and ethical dimensions of creativity.Using 20k artworks from the SemArt dataset, we annotate images with GPT 4.1 using detailed, theory-aligned prompts, and evaluate the learnability of these traits from CLIP image embeddings. Traits such as Environmental Dialogicity and Redemptive Arc are predicted with high reliability ($R^2 \approx 0.64 - 0.68$), while others like Memory Imprint remain challenging, highlighting the limits of purely visual encoding. Beyond technical metrics, we visualize a "creativity trait-space" and illustrate how it can support interpretable, trait-aware co-creation - e.g., sliding along a Redemptive Arc axis to explore works of adversity and renewal. By linking cultural-aesthetic insights with computational modeling, our work aims not to reduce creativity to numbers, but to offer shared language and interpretable tools for artists, researchers, and AI systems to collaborate meaningfully.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
