Wu Yankun, Nakashima Yuta, Garcia Noa
Intelligence and Sensing Lab, Osaka University, Suita 565-0871, Osaka, Japan.
J Imaging. 2024 Jun 26;10(7):156. doi: 10.3390/jimaging10070156.
The content-style duality is a fundamental element in art. These two dimensions can be easily differentiated by humans: content refers to the objects and concepts in an artwork, and style to the way it looks. Yet, we have not found a way to fully capture this duality with visual representations. While style transfer captures the visual appearance of a single artwork, it fails to generalize to larger sets. Similarly, supervised classification-based methods are impractical since the perception of style lies on a spectrum and not on categorical labels. We thus present , which captures the artistic knowledge of a cutting-edge generative model for disentangling content and style in art. Experiments show that explicitly learns to represent the two artistic dimensions (content and style) of the original artistic image, paving the way for leveraging generative models in art analysis.
内容风格二元性是艺术中的一个基本要素。人类能够轻易区分这两个维度：内容指艺术品中的对象和概念，而风格则指其外观呈现方式。然而，我们尚未找到一种通过视觉表征来完全捕捉这种二元性的方法。虽然风格迁移能够捕捉单个艺术品的视觉外观，但无法推广到更大的集合。同样，基于监督分类的方法也不切实际，因为风格的感知存在于一个连续谱上，而非类别标签。因此，我们提出了 ，它捕捉了一种前沿生成模型的艺术知识，用于在艺术中解开内容和风格。实验表明， 明确学会了表征原始艺术图像的两个艺术维度（内容和风格），为在艺术分析中利用生成模型铺平了道路。
