TL;DR本文提出了一种新的神经样式转换模型,它是基于无需相关风格图像,可用于任何内容和风格的输入形成语义准确的生成图像,规避了全模型训练的烦恼,并通过单向 GAN 模型的确保循环一致性的结构,实现了更高效的训练和验证阶段以及更小的模型尺寸。
Abstract
A neural artistic style transformation (nst) model can modify the appearance of a simple image by adding the style of a famous image. Even though the transformed images do not look precisely like artworks by the