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

Image style conversion and model training method and device

A style conversion and style technology, applied in the field of image processing, can solve problems such as blurred image effects

Active Publication Date: 2020-10-23
BEIJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the purpose of the present invention is to propose a method and device for image style conversion and model training, to improve the adaptability of image style conversion in a variety of different scenarios, and to improve image blurring and image blurring after style conversion. The problem of poor effect, while achieving coarse-grained and fine-grained high-quality image style transfer

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 and model training method and device
  • Image style conversion and model training method and device
  • Image style conversion and model training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0077]It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present invention shall have the usual meanings understood by those skilled in the art to which the present disclosure belongs. "First", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Comprising" or "comprising" and similar words mean that the elements or items appearing before the word include the elements or items listed after the word and their equivalents, without excluding other elements or items. Words such as "connected" or "connected" are not limited to physical or mechani...

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 and model training method and device. The method comprises the steps of: respectively inputting a first style image and a second style image into a content encoder and a style encoder in an encoder network, and respectively extracting a content encoding feature image and a style encoding feature image; respectively inputting the style and the content coding feature image into a decoder network to obtain a target image converted from a first style to a second style. According to the method, an image style conversion model formed by the coder anddecoder networks is obtained by pre-training an image training sample comprising a plurality of first and second style images and instance images cut from the image training sample. By applying the method, the style conversion adaptability to various different scenes can be improved, the problems of image blurring and poor instance effect in the image after style conversion are improved, and meanwhile, coarse-grained and fine-grained high-quality image style migration is realized.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and device for image style conversion and model training. Background technique [0002] Image style transfer is an important content in the field of image processing. With the development of society and economy, there are more and more demands for audio and video processing, especially focusing on face editing / generation, image enhancement, and image style conversion. Apps / cameras that apply related technologies are easy to attract people's attention. Create economic and social value. Using the image style conversion technology to enhance the image, the image at night can be enhanced to obtain an image with clearer information, thereby greatly improving the visibility of the image, which is of great significance for video surveillance. With the increasing development and improvement of digital image processing, pattern recognition and deep learning tec...

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): G06T3/00G06T9/00G06T7/11
CPCG06T9/002G06T7/11G06T2207/10024G06T2207/10048G06T2207/20081G06T2207/20084G06T2207/20132G06T3/04
Inventor 傅慧源马华东余艇张宇
Owner BEIJING UNIV OF POSTS & TELECOMM
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com