论文标题
缪斯：文字属性指导肖像画一代
MUSE: Textual Attributes Guided Portrait Painting Generation
论文作者
论文摘要
我们提出了一种新颖的方法缪斯，以通过肖像产生为视觉说明文本属性。除了从主题的照片中提取的面部特征外，缪斯（Muse）采用了一组用文本写的属性。我们提出11种属性类型，以代表主题的个人资料，情感，故事和环境中的灵感。我们通过扩展图像到图像生成模型来接受文本属性来提出一种新颖的堆叠神经网络体系结构。实验表明，我们的方法在不使用文本属性的情况下明显胜过几种最先进的方法，其成立得分分别增加了6％，而Fréchet成立距离（FID）得分分别下降了11％。我们还提出了一个新的属性重建度量，以评估生成的肖像是否保留对象的属性。实验表明，我们的方法可以准确说明78％的文本属性，这也有助于以更具创造力和表现力的方式捕捉主题。
We propose a novel approach, MUSE, to illustrate textual attributes visually via portrait generation. MUSE takes a set of attributes written in text, in addition to facial features extracted from a photo of the subject as input. We propose 11 attribute types to represent inspirations from a subject's profile, emotion, story, and environment. We propose a novel stacked neural network architecture by extending an image-to-image generative model to accept textual attributes. Experiments show that our approach significantly outperforms several state-of-the-art methods without using textual attributes, with Inception Score score increased by 6% and Fréchet Inception Distance (FID) score decreased by 11%, respectively. We also propose a new attribute reconstruction metric to evaluate whether the generated portraits preserve the subject's attributes. Experiments show that our approach can accurately illustrate 78% textual attributes, which also help MUSE capture the subject in a more creative and expressive way.
