Creative Blends of Visual Concepts
Zhida Sun, Zhenyao Zhang, Yue Zhang, Min Lu, Dani Lischinski, Daniel, Cohen-Or, Hui Huang

TL;DR
This paper introduces Creative Blends, an AI-assisted system that uses metaphors and generative models to create visually rich blends of abstract concepts, reducing cognitive load and fostering creativity.
Contribution
We present a novel AI system that combines commonsense knowledge, language models, and generative image techniques to enhance visual blending of abstract concepts.
Findings
User study shows reduced cognitive load
Enhanced metaphorical richness in visual blends
Fosters creativity in design process
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
