Image style migration method and device based on generative adversarial network and related equipment

An image and style technology, applied in the field of image processing, can solve problems such as huge cost, complex operation, and huge data set

Active Publication Date: 2021-10-22
深圳市安软科技股份有限公司 +1
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the demand for data sets used to train GAN models is getting larger and larger,

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image style migration method and device based on generative adversarial network and related equipment
  • Image style migration method and device based on generative adversarial network and related equipment
  • Image style migration method and device based on generative adversarial network and related equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] Referring to the drawings, wherein like reference numerals represent like components, the principles of the present invention are exemplified when implemented in a suitable computing environment. The following description is based on illustrated specific embodiments of the invention, which should not be construed as limiting other specific embodiments of the invention not described in detail herein.

[0052] refer to figure 1 In an image style transfer method based on a generative confrontation network provided by an embodiment of the present invention, it specifically includes the following steps:

[0053] Step S101: Construct a generative confrontation network model including a generator and a discriminator, and initialize the weight parameters of the generator, which includes an encoder and self-attention mechanism module, the encoder Includes content mask generator and the attention mask generator .

[0054] Wherein, the weight parameters of the generator i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the invention discloses an image style migration method and device based on a generative adversarial network and related equipment. The method comprises the following steps: constructing a generative adversarial network model comprising a generator and a discriminator, and initializing the weight parameter of the generator, wherein the generator comprises an encoder and a self-attention mechanism module, and the encoder comprises a content mask generator and an attention mask generator; then obtaining a training sample image; training the generative adversarial network model by using the training sample image until the generator and the discriminator reach Nash equilibrium; and inputting an image to be subjected to style migration into the trained generative adversarial network model to obtain an image after style migration. By means of the mode, style migration of the images can be achieved, diversified images are generated, and data sets can be expanded easily.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image style transfer method, device and related equipment based on a generative confrontation network. Background technique [0002] With the improvement of computing power and the sharp increase in the amount of data in various industries, artificial intelligence has achieved rapid development. The academic community generally believes that artificial intelligence can be divided into two stages: the perception stage and the cognitive stage. In the cognitive stage, machines can have a certain understanding of the nature of the world, and the so-called "understanding" is an internal performance of both humans and artificial intelligence, which cannot be directly measured, but can only be indirectly inferred from other aspects. As a typical generative model, Generative Adversarial Networks (GAN) has the ability of its generator to generate data samples, which re...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T3/00G06K9/62G06N3/04G06N3/08
CPCG06T3/0012G06N3/08G06N3/048G06N3/045G06F18/214
Inventor 刘建征杨巨成姚彤张伟许能华闫潇宁
Owner 深圳市安软科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap