Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image style conversion method and device and electronic equipment

A style conversion and image technology, applied in the field of image processing, can solve problems such as the inability to guarantee the effect of image area conversion, and achieve the effect of improving style conversion effect and conversion quality.

Pending Publication Date: 2022-08-02
HANGZHOU HIKVISION DIGITAL TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides an image style conversion method, device, and electronic equipment to at least solve the problem that in the prior art, when performing image style conversion based on an adversarial network, the style conversion can only be performed as a whole and cannot guarantee the conversion effect of a predetermined area in the image. The problem

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 conversion method and device and electronic equipment
  • Image style conversion method and device and electronic equipment
  • Image style conversion method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] It should be noted that the embodiments in the present application and the features of the embodiments may be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0027] It should be noted that the steps shown in the flowcharts of the accompanying drawings may be executed in a computer system, such as a set of computer-executable instructions, and, although a logical sequence is shown in the flowcharts, in some cases, Steps shown or described may be performed in an order different from that herein.

[0028] In the following embodiments, a generative adversarial network is used to convert the image style, and the adversarial network is first introduced.

[0029] The generative adversarial network generally includes two parts: the generator (or called the generator model, the generator in English is Generator, so it can be repre...

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 invention discloses an image style conversion method and apparatus, and an electronic device. The method comprises the steps of obtaining data; a generator model and a discriminator model are constructed, the generator model is used for generating a simulation style image according to the content image and generating a simulation style area image according to the content area image, and the style of the image generated by the generator model is the same as that of the style image; the discriminator model is used for predicting the probability that the image input into the model is generated by the generator model; performing unsupervised training on the generator model and the discriminator model by using the data to obtain a trained generator model; and performing image style conversion by using the trained generator model. The image style conversion method and device solve the problem that in the prior art, when image style conversion is carried out based on an adversarial network, style conversion can only be carried out on the whole, and the conversion effect of the preset area in the image cannot be guaranteed, can improve the style conversion effect of the preset area in the image, and then improve the conversion quality of the image.

Description

technical field [0001] The present application relates to the field of image processing, and in particular, to an image style conversion method, device and electronic device. Background technique [0002] The goal of image style transfer is to convert a given image to a specified style, keeping the content unchanged. [0003] Most of the existing image style transfer methods use generative adversarial networks for training to learn the feature information and semantic relationship between the content image and the style image, and realize the conversion of the content image to a specific style; among them, the content image needs to be styled. Image, style image is an image with a specified style that is the target of the content image transformation. [0004] In the prior art, the effect of the entire generated image obtained after the content image is converted is generally used as the optimization target of model training, and the conversion effect of the key region of i...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T3/00G06N3/04G06N3/08
CPCG06N3/088G06N3/045G06T3/04Y02T10/40
Inventor 施登科张睿轩陈杰
Owner HANGZHOU HIKVISION DIGITAL TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products