arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.16062cs.HCcs.GR
收藏

视觉概念的创意融合

Creative Blends of Visual Concepts

Zhida Sun, Zhenyao Zhang, Yue Zhang, Min Lu, Dani Lischinski, Daniel Cohen-Or, Hui Huang

AI总结:

针对视觉融合传达抽象概念的概念与技术挑战,提出AI辅助设计系统Creative Blends,结合常识知识库、大语言模型与文本生成图像技术实现视觉融合,经用户研究验证可降低认知负荷、激发创造力并提升隐喻丰富度,还探索了多物体融合的潜力。

摘要:

视觉融合将两种截然不同的视觉概念的元素结合成单一的整合图像,目标是通过富有想象力且通常发人深省的视觉效果传达思想。通过视觉融合传达抽象概念带来了一系列概念和技术层面的挑战。为应对这些挑战,我们推出了Creative Blends(创意融合),这是一个AI辅助设计系统,它利用隐喻,通过融合不同的物体来视觉化象征抽象概念。我们的方法利用常识知识库和大语言模型,将设计师的概念意图与富有表现力的具体物体对齐。此外,我们采用生成式文本到图像技术,通过视觉元素的重叠属性来融合这些元素。一项包含24名参与者(N=24)的用户研究表明,我们的方法降低了参与者的认知负荷,激发了创造力,并提升了视觉融合构思的隐喻丰富度。我们探索了该方法将视觉融合扩展至多物体融合的潜力,并讨论了在使用生成式AI进行设计的过程中获得的见解。

英文摘要:

Visual blends combine elements from two distinct visual concepts into a single, integrated image, with the goal of conveying ideas through imaginative and often thought-provoking visuals. Communicating abstract concepts through visual blends poses a series of conceptual and technical challenges. To address these challenges, we introduce Creative Blends, an AI-assisted design system that leverages metaphors to visually symbolize abstract concepts by blending disparate objects. Our method harnesses commonsense knowledge bases and large language models to align designers' conceptual intent with expressive concrete objects. Additionally, we employ generative text-to-image techniques to blend visual elements through their overlapping attributes. A user study (N=24) demonstrated that our approach reduces participants' cognitive load, fosters creativity, and enhances the metaphorical richness of visual blend ideation. We explore the potential of our method to expand visual blends to include multiple object blending and discuss the insights gained from designing with generative AI.

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。

↑