Structure-Preserving Neural Style Transfer
Abstract
State-of-the-art neural style transfer methods have demonstrated amazing results by training feed-forward convolutional neural networks or using an iterative optimization strategy. The image representation used in these methods, which contains two components: style representation and content representation, is typically based on high-level features extracted from pre-trained classification networks. Because the classification networks are originally designed for object recognition, the extracted features often focus on the central object and neglect other details. As a result, the style textures tend to scatter over the stylized outputs and disrupt the content structures. To address this issue, we present a novel image stylization method that involves an additional structure representation. Our structure representation, which considers two factors: i) the global structure represented by the depth map and ii) the local structure details represented by the image edges, effectively reflects the spatial distribution of all the components in an image and the structure of dominant objects respectively. Experimental results demonstrate that our method achieves impressive visual effects, which is particularly significant when processing images sensitive to structure distortion, e.g., images containing multiple objects potentially at different depths, or dominant objects with clear structures.
Paper
- Structure-Preserving Neural Style Transfer, Ming-Ming Cheng#*, Xiao-Chang Liu#, Jie Wang, Shao-Ping Lu, Yu-Kun Lai, Paul L. Rosin, IEEE TIP, 29:909-920, 2020. [pdf | bib | project | code]
您好,看了这篇文章后我发现大多都是艺术风格转换,我想问一下这个算法对真实图像的转换怎么样
这个没尝试过。结构保持理论上对真实图像转换也是有意义的。
谢谢
有幸拜读到这篇文章,但在编程实现做些图片时遇到了障碍,希望能看到您的源码
代码链接:https://github.com/xch-liu/structure-nst
请问代码还准备开源吗
代码链接已更新
请问这个项目有公开代码吗
前一段时间在忙CVPR 2020。近期会整理代码再放出
代码已更新