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

An image local style transfer method based on decomposition factor

A style and image technology, applied in the field of image local style transfer based on decomposition factors, can solve problems such as translation of specified objects without research

Active Publication Date: 2019-03-08
聚时科技(上海)有限公司
View PDF7 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, these style transfer tasks mainly map the distribution of the whole image to the corresponding distribution, or factor translation in one domain, while no study translates the specified object in a different domain while keeping the rest unchanged.

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
  • An image local style transfer method based on decomposition factor
  • An image local style transfer method based on decomposition factor
  • An image local style transfer method based on decomposition factor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is carried out on the premise of the technical solution of the present invention, and detailed implementation and specific operation process are given, but the protection scope of the present invention is not limited to the following embodiments.

[0034] 1. Related technologies

[0035] 1) Autoencoder

[0036] Autoencoder is an effective unsupervised learning encoding method, and as a basic model, it is widely used in image translation tasks. Its purpose is to learn a representation of the input data, which is often applied to dimensionality reduction. An autoencoder includes an input layer, an output layer, and one or more hidden layers. The training goal is to reconstruct its input, which can be defined as a mapping Φ:x→ω and ψ:ω→x, such that

[0037]

[0038] where Φ, ψ, ω and x ∈ X denote encoder, decoder, encoding an...

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 relates to an image local style migration method based on a decomposition factor. The method comprises the following steps of 1) acquiring a migration task; 2) initializing that style migration network and training with tag data samples; 3) processing the migration task based on the trained style migration network to obtain a composite image, wherein the style migration network comprises two automatic encoders and four tag classifiers, each automatic encoder comprises one encoder and two decoders, the tag classifier is arranged between the encoder and the decoder, and the encoderrealizes the decomposition of a specified factor and a common factor. Compared with the prior art, the method of the invention can better decouple factors, and has the advantages of remarkable reconstruction effect and the like.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image local style transfer method based on decomposition factors. Background technique [0002] Style transfer falls under the category of vision and graphics problems, where the goal is to learn a mapping between an input distribution and an output distribution. With the development of deep learning, deep neural network has become the most commonly used mapping learning method and has achieved state-of-the-art performance. [0003] Traditionally, maps are trained from a set of pixel-to-pixel aligned image pairs with corresponding relationships. For example, some researchers focus on learning pixel-wise mappings for this task, especially generative adversarial networks (GANs) and autoencoders, which are widely used in image translation due to their powerful image generation capabilities. For example, the pix2pix algorithm generates real images based on conditional G...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/088G06N3/045G06F18/214G06F18/24
Inventor 郑军刘新旺
Owner 聚时科技(上海)有限公司
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