arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.07208cs.CVcs.LG
收藏

基于特征分布的神经风格迁移的矩匹配

In the light of feature distributions: moment matching for Neural Style Transfer

ETH Zürich(苏黎世联邦理工学院)

Nikolai Kalischek, Jan Dirk Wegner, Konrad Schindler

摘要:

风格转换旨在以另一个图像的图形/艺术风格呈现给定图像的内容。NeuralStyle Transfer(NST)的基本概念是将风格解释为卷积神经网络的特征空间中的分布,使得可以通过匹配其特征分布来实现期望的风格。我们表明,该概念的大多数当前实现具有重要的理论和实践局限性,因为它们仅部分对齐特征分布。我们提出了一种新的方法,更精确地匹配的分布,从而更忠实地再现所需的风格,同时仍然是计算效率。具体来说,我们适应的双重形式的中心矩离散(CMD),最近提出的领域自适应,以尽量减少目标风格和输出图像的特征分布之间的差异。该度量的双重解释明确匹配所有高阶集中矩,因此是仅考虑一阶和二阶矩的现有NST方法的自然扩展。我们的实验证实,强大的理论属性也转化为视觉上更好的风格转移,更好地从语义图像内容的风格。

英文摘要:

Style transfer aims to render the content of a given image in the graphical/artistic style of another image. The fundamental concept underlying NeuralStyle Transfer (NST) is to interpret style as a distribution in the feature space of a Convolutional Neural Network, such that a desired style can be achieved by matching its feature distribution. We show that most current implementations of that concept have important theoretical and practical limitations, as they only partially align the feature distributions. We propose a novel approach that matches the distributions more precisely, thus reproducing the desired style more faithfully, while still being computationally efficient. Specifically, we adapt the dual form of Central Moment Discrepancy (CMD), as recently proposed for domain adaptation, to minimize the difference between the target style and the feature distribution of the output image. The dual interpretation of this metric explicitly matches all higher-order centralized moments and is therefore a natural extension of existing NST methods that only take into account the first and second moments. Our experiments confirm that the strong theoretical properties also translate to visually better style transfer, and better disentangle style from semantic image content.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑