创意连接与视觉概念表达的沉浸式空间

摘要

创造新颖的视觉概念往往需要通过不同想法之间最相关的共享属性——即它们的「氛围特征」——来建立连接。本文提出「氛围融合」这一新任务，旨在生成连贯且有意义的混合图像，以揭示图像间潜在的共享属性。现有方法难以在潜在空间中识别并穿越连接远距离概念的非线性路径，因此实现此类融合具有挑战性。我们构建了「氛围空间」——一种分层图流形，能在CLIP等特征空间中学习低维测地线，从而实现概念间平滑且语义一致的过渡。为评估创意质量，我们设计了融合人类判断、大语言模型推理与基于几何路径的难度评分的认知启发式框架。实验表明，相较于现有方法，氛围空间生成的融合图像在人类评估中持续获得更高创意性与连贯性评分。

English

Creating new visual concepts often requires connecting distinct ideas through their most relevant shared attributes -- their vibe. We introduce Vibe Blending, a novel task for generating coherent and meaningful hybrids that reveals these shared attributes between images. Achieving such blends is challenging for current methods, which struggle to identify and traverse nonlinear paths linking distant concepts in latent space. We propose Vibe Space, a hierarchical graph manifold that learns low-dimensional geodesics in feature spaces like CLIP, enabling smooth and semantically consistent transitions between concepts. To evaluate creative quality, we design a cognitively inspired framework combining human judgments, LLM reasoning, and a geometric path-based difficulty score. We find that Vibe Space produces blends that humans consistently rate as more creative and coherent than current methods.

创意连接与视觉概念表达的沉浸式空间

Vibe Spaces for Creatively Connecting and Expressing Visual Concepts

摘要

Support