Style learning with feature-based texture synthesis
Style learning with feature-based texture synthesis
复制标题
通过基于特征的纹理合成进行风格学习
DOI：
10.1145/1461999.1462010
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
S. H. Soon
中科院分区：
文献类型：
--
作者：
Xuexiang Xie;Feng Tian;S. H. Soon
艺术风格学习的目标是从源图像与从示例图像中学习的风格合成新图像。现有的基于示例的纹理合成 (EBTS) 技术使用低级统计属性对样式进行建模。这些方法适用于某些艺术风格（例如油画），但难以保留其他风格（例如铅笔阴影）的图像细节和特征。在本文中，介绍了一种基于特征的纹理合成（FBTS）的改进的艺术风格学习算法。与现有的 EBTS 方法相比，在我们的 FBTS 算法中，通过源图像生成的特征场更好地定义了图像细节和特征。此外，还提出了一种改进的 L2 邻域距离度量，它提供了更好的感知相似性度量。结果和比较证明了 FBTS 算法在风格化着色和艺术风格迁移领域的应用的有效性。
The objective of artistic style learning is to synthesize a new image from a source image with the style learnt from example images. Existing example-based texture synthesis (EBTS) techniques model style with low-level statistical properties. These methods work well with some artistic styles such as oil painting, but have difficulties in preserving image details and features for other styles such as pencil hatching. In this article, an improved artistic style-learning algorithm with feature-based texture synthesis (FBTS) is introduced. Compared with existing EBTS methods, in our FBTS algorithm, image details and features are better defined with a feature field generated from the source image. Also, an improved L2 neighborhood distance metric which provides better measures of perceptual similarity is proposed. Results and comparisons are given to demonstrate the effectiveness of the FBTS algorithm with applications in the areas of stylized shading and artistic style transfer.