Geometry and shape are fundamental aspects of visual style. Existing style transfer methods focus on texture-like components of style, ignoring geometry. We propose deformable style transfer (DST), an optimization-based approach that integrates texture and geometry style transfer. Our method is the first to allow geometry-aware stylization not restricted to any domain and not requiring training sets of matching style/content pairs. We demonstrate our method on a diverse set of content and style images including portraits, animals, objects, scenes, and paintings.
翻译:几何和形状是视觉风格的基本方面。 现有的样式转换方法侧重于风格的质地相似的元素, 忽略几何。 我们建议采用变形样式转换( DST), 这是一种以优化为基础的方法, 将质地和几何样式转换结合起来。 我们的方法是首先允许不局限于任何领域也不需要匹配样式/ 内容配对的培训组合。 我们用多种内容和样式图像展示我们的方法, 包括肖像、 动物、 对象、 场景和绘画。