融合超分辨率重构的图像任意风格迁移  

Image Arbitrary Style Transfer via Super-Resolution Reconstruction

作　　者：谭润 田启川 廉露 张晓行 TAN Run;TIAN Qichuan;LIAN Lu;ZHANG Xiaohang(College of Electrical and Information Engineering,Beijing University of Civil Engineering and Architecture,Beijing 100044,China)

机构地区：[1]北京建筑大学电气与信息工程学院,北京100044

出　　处：《计算机工程与应用》2024年第15期170-179,共10页Computer Engineering and Applications

基　　金：北京建筑大学研究生教育教学质量提升项目(J2022012);北京建筑大学研究生创新项目。

摘　　要：图像风格迁移是指将一张普通照片转化为具有其他艺术风格效果的图像。针对风格迁移算法中无法重构生成图像的分辨率而造成生成图像清晰度低、纹理细节表现不丰富的问题,提出一种融合超分辨率重构的图像任意风格迁移模型。模型中加入的多支路特征处理模块通过计算特征的自相似性以增强特征的表达,提出新的特征融合模块以提升特征融合效果,提出特征解码模块来实现图像的超分辨率重构,并在其中多次进行特征融合以提升风格化图像的质量;在损失函数中加入生成对抗损失和白化处理来进一步提升风格化效果。实验表明,模型具有较好的任意风格迁移效果,分辨率重构后的风格化图像的细节丰富、纹理清晰。Image style transfer refers to the transformation of an ordinary photograph into an image with other artistic style effects.To address the problems of low definition and lack of texture details in the generated image due to the inability to reconstruct the resolution of the generated image in style transfer algorithms,an image arbitrary style transfer via super-resolution reconstruction is proposed.The multi-channel feature processing module added in the model enhances the fea-ture expression by calculating the feature self-similarity,and a feature fusion module is proposed to improve the feature fusion effect.A feature decoder module is proposed to realize the image super-resolution reconstruction,in which features are fused several times to improve the stylized image quality.In the loss function,generative adversarial loss and whiten-ing process are added to further improve the stylization effect.The experiment shows the model has great arbitrary style transfer effect,and the stylized image during resolution reconstruction has rich details and clear texture.

关 键 词：任意风格迁移 超分辨率重构 生成对抗网络 自注意力机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]