• 图形图像 •

### 改进型任意风格快速迁移元网络算法

1. 江西师范大学 计算机信息工程学院，南昌 330022
• 出版日期:2020-05-01 发布日期:2020-05-08

### Improved Algorithm for Fast Arbitrary Style Transfer Meta Network

LIU Yunxin, JIANG Aiwen, YE Jihua, WANG Mingwen

1. School of Computer and Information Engineering, Jiangxi Normal University, Nanchang 330022, China
• Online:2020-05-01 Published:2020-05-08

Abstract:

The fast arbitrary style transfer based on meta-networks has attracted great attention and high praise. However, visible gray blocks of stylistic incongruity often appear in stylized result image. The hue of stylized result image is often not consistent with target style image, which severely affects qualities of final transfer results. This paper proposes an improvement strategy. Gram matrix is used as a style statistic for meta network input and loss computing. By integrating the average pooling operation of Gram matrix and the grouped full connection strategy of meta-network, this paper effectively avoids the problem of too large network parameters brought by traditional Gram matrix. Experimental results show that the method can not only effectively eliminate the incongruous style block problem, but also achieve better visual effect than the original method in texture and color layout. Through theoretical analysis and experimental evidence, this paper confirms the superiority of using Gram matrix as style loss and feature statistics on convergence and visual effect.