Algum conteúdo deste aplicativo está indisponível no momento.
Se esta situação persistir, por favor entre em contato conoscoFale conosco & Contato
1. (CN106651766) Image style migration method based on deep convolutional neural network

Organismo : China
Número do pedido: 201611252944.3 Data do pedido: 30.12.2016
Número de publicação: 106651766 Data de publicação: 10.05.2017
Tipo de publicação : A
CIP:
G06T 3/00
G FÍSICA
06
CÔMPUTO; CÁLCULO; CONTAGEM
T
PROCESSAMENTO DE DADOS DE IMAGEM OU GERAÇÃO, EM GERAL
3
Transformação de imagem geométrica no plano da imagem, p. ex.,de bit-mapped para bit-mapped criando uma imagem diferente
Requerentes: SHENZHEN WETECCTV SCIENCE & TECHNOLOGY CO., LTD.
Inventores: XIA CHUNQIU
Dados da prioridade:
Título: (EN) Image style migration method based on deep convolutional neural network
(ZH) 一种基于深度卷积神经网络的图像风格迁移方法
Resumo: front page image
(EN) The invention discloses an image text description method based on a visual attention model. The main content comprises the followings: image inputting, loss function training, stylizing, image enhancing and image thinning; and the processes are as follows: an input image is firstly adjusted as a content image (256*256) with a dual-linear down-sampling layer, and then stylized through a style subnet; and then a stylized result as the first output image is up-sampled as an image in the size of 512*512, and then the up-sampled image is enhanced through an enhancement subnet to obtain the second output image; the second output image is adjusted as the image in the size of 1024*1024, and finally, a thinning subnet deletes locally pixelated artifact and further thins the result to obtain a high-resolution result. By use of the image style migration method disclosed by the invention, the brushwork of the artwork can be simulated more closely; multiple models are combined into a network so as to process the image with bigger and bigger size shot by a modern digital camera; and the method can be used for training the combined model to realize the migration of multiple artistic styles.
(ZH) 本发明中提出的一种基于视觉注意模型的图像文字描述方法,其主要内容包括:图像输入、损失函数训练、风格化、图像增强、图像细化,其过程为,输入图像首先被调整为具有双线性下采样层的内容图像(256×256),通过风格子网风格化;接着,作为第一输出图像的风格化结果被上采样为512×512大小的图像,并且通过增强子网得到第二输出图像;然后,它被调整大小为1024×1024;最后,细化子网删除局部像素化伪影,并进一步细化结果,获得高分辨率结果。本发明可以更密切地模拟艺术品的笔触;将多个模型组合到一个网络中,能够处理现代数码相机拍摄得到的尺寸越来越大的图像;它还可以用于训练组合模型,实现多个艺术风格迁移。