构建首个大规模抽象艺术数据集，助力AI理解视觉语言。
Abstract4D: A Large-Scale Dataset and Framework for Understanding the Visual Language of Abstract Art
- 构建12万+抽象画图像数据集，含四维感知标注
- 揭示感知关系如何组织抽象艺术意义
- 提供分类、跨模态检索等评测基准，适合艺术与AI交叉研究者
人工智能可分类艺术风格并生成图像，但缺乏对赋予艺术意义的视觉语言模型。抽象绘画弱化物体语义，突出结构线索，是计算感知的理想测试平台。我们提出【Abstract4D】——迄今最大的抽象绘画数据集：包含超过12万张图像，配有丰富的元数据和多维度提示，涵盖每幅作品的【形式、色彩、纹理、构图】四大感知属性。标注通过人机协同的VLM流水线完成，确保质量与一致性。利用Abstract4D，我们（i）通过大规模嵌入可视化分析抽象艺术的语义结构，揭示感知关系如何组织艺术意义；（ii）建立分类、跨模态检索、文本到图像生成三项基准任务，评估AI模型对抽象视觉语言的理解与再现能力。这些工作共同证明，Abstract4D能实现对AI表征与解读抽象艺术能力的探索与量化评估。
原文摘要 · Abstract (English)
Artificial intelligence can classify artistic styles and synthesize images, but it still lacks a model of the visual language that gives art meaning. Abstract painting minimizes object semantics and foregrounds structural cues, making it an ideal testbed for computational perception. We introduce \textbf{Abstract4D}, the largest dataset of abstract paintings to date: more than 120,000 images paired with rich metadata and multi-dimensional prompts that capture each work's perceptual attributes---\textit{form, color, texture, and composition}. Annotations are produced by a hybrid human--VLM pipeline for quality and consistency. Using Abstract4D, we (i) analyze the semantic structure of abstract art through large-scale embedding visualization, uncovering how perceptual relationships organize artistic meaning, and (ii) establish benchmark tasks for classification, cross-modal retrieval, and text-to-image generation to evaluate how AI models perceive and reproduce abstract visual language. Together, these analyses demonstrate how Abstract4D enables both exploration and quantitative assessment of AI's ability to represent and interpret abstract art.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。