TL;DR该论文提出了一个基于 GAN 框架的新方法,用于从简笔画和风格参考图像中合成带有颜色和纹理的详细艺术风格图像;该方法采用了双重遮罩机制、特征映射转换技术以及反实例标准化过程等模块,以增强风格一致性和内容约束,并取得了显著的合成性能提升。
Abstract
We propose a new approach for synthesizing fully detailed art-stylized images from sketches. Given a sketch, with no semantic tagging, and a reference image of a specific style, the model can synthesize meaningfu