摘要
不同于艺术风格迁移,真实图像风格迁移的挑战在于,迁移结果在迁移风格图片的色调风格的同时在内容上应保持真实性。目前,真实图像风格迁移的方法往往是在艺术风格迁移方法的基础上进行预处理或后处理,以保持生成图片的真实性。但艺术风格迁移方法通常无法充分利用全局色彩信息实现更为协调的整体观感,且预处理和后处理操作往往繁琐而费时。针对以上问题,建立了全局信息引导的真实图像风格迁移网络,提出了色域均值损失(L_(cpm))来衡量生成图片与风格图片全局色彩分布的相似性,对自适应实例归一化(AdaIN)进行改进,提出分区自适应实例归一化(AdaIN-P),以更好地适应真实图像的色彩风格迁移;此外,引入了一种跨通道分区注意力机制,以更好地利用全局上下文信息,提升生成图片的整体协调性。上述方法能够引导网络解码器充分利用全局信息。实验结果表明,相较于其他主流方法,所提网络模型能在保持图像细节的同时实现更好的真实图像风格迁移效果。
Different from artistic style transfer,the challenge of photorealistic style transfer is to maintain the authenticity of the output while transferring the color style of the style input.Now,most photorealistic style transfer methods perform pre-proces-sing or post-processing based on artistic style transfer methods,to maintain the authenticity of the output image.However,artistic style transfer methods usually cannot make full use of global color information to achieve a more coordinated overall impression,and pre-processing and post-processing operations are often tedious and time-consuming.To solve the above problems,this paper establishes a photorealistic style transfer network guided by global information,and proposes a color-partition-mean loss(L_(cpm))to measure the similarity of the global color distribution between output and the style input.Adaptive instance normalization(AdaIN)is improved,and partition adaptive instance normalization(AdaIN-P)is proposed to better adapt to the color style transfer of real images.In addition,this paper also introduces a cross-channel partition attention module to make better use of global context information and improve the overall coordination of output images.Through the above methods,the decoder of network is guided to make full use of global information.Experimental results show that,compared with other state-of-the-art me-thods,the proposed model can achieve a better photorealistic style transfer effect while maintaining image details.
作者
张颖涛
张杰
张睿
张文强
ZHANG Ying-tao;ZHANG Jie;ZHANG Rui;ZHANG Wen-qiang(School of Computer Science,Fudan University,Shanghai 200011,China;Shanghai Key Laboratory of Intelligent Information Processing,Fudan University,Shanghai 200011,China)
出处
《计算机科学》
CSCD
北大核心
2022年第7期100-105,共6页
Computer Science
关键词
风格迁移
全局信息
卷积神经网络
注意力机制
编码解码
特征融合
Style transfer
Global information
Convolution neural network
Attention mechanism
Encoder and decoder
Feature fusion
