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

Multi-domain image style migration method based on generative adversarial network

An image and style technology, applied in the field of computer vision, can solve the problem of lack of diversity in output

Active Publication Date: 2019-10-08
DALIAN UNIV OF TECH
View PDF3 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] However, an important problem with CycleGAN is that the output lacks diversity and can only simulate a certain distribution

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
  • Multi-domain image style migration method based on generative adversarial network
  • Multi-domain image style migration method based on generative adversarial network
  • Multi-domain image style migration method based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The invention provides a multi-domain image style transfer method based on generating confrontation network. The specific embodiments discussed are merely illustrative of implementations of the invention, and do not limit the scope of the invention. Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, specifically including the following steps:

[0040] 1. Image preprocessing: Take the transfer task of converting photos into Monet, Ukiyo-e, and Van Gogh styles as an example. From the real data distribution x i , i = 1, 2, 3, 4 are sampled to get the real image x i , where we take the real image x 1 It is called a real source domain image, that is, a photo of a real scene with a pixel size of 256*256; the real image x i , i=2, 3, 4 is called the real target domain image, that is, the works of Monet, Ukiyo-e and Van Gogh with a pixel size of 256*256. Using Python's image processing module, the real sour...

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 provides a multi-domain image style migration method based on a generative adversarial network, and belongs to the field of computer vision, for realizing conversion from an image to multiple different artistic styles. The multi-domain image style migration method designs an expert style network, and extracts style feature codes containing unique information of respective domains ininput images of different target domains through a group of bidirectional reconstruction losses. Meanwhile, the multi-domain image style migration method designs a migration network, and recombines extracted style feature codes and cross-domain shared semantic contents extracted by a content encoder to generate a new image in combination with self-adaptive instance standardization, so that style migration of the image from a source domain to a plurality of target domains is realized. Experiments show that the model can effectively combine the content of any photo with the styles of a pluralityof artworks to generate a new image.

Description

technical field [0001] The invention belongs to the field of computer vision and relates to a multi-domain image style transfer method based on a generation confrontation network. Background technique [0002] In recent years, artificial intelligence technology led by deep learning has been widely used in various fields. Among them, the collision of deep learning and art has attracted the attention of researchers. Various image processing software and applications based on related technologies have also attracted a large number of users. The core of which is image style transfer based on deep learning. Deep learning can capture the content of one image and combine it with the style of another image, a technique known as style transfer. [0003] The style transfer problem arises from non-photorealistic rendering (Kyprianidis J E, Collomosse J, Wang T, et al. State of the art: A taxonomy of artistic stylization techniques for images and video. TVCG, 2013.), and with texture...

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): G06T3/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06T3/04
Inventor 葛宏伟姚瑶孙克乙张强孙亮
Owner DALIAN UNIV OF 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

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