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

Image editing method, training method of image editing model, equipment and device

An image editing and editing technology, applied in the field of image processing, can solve the problems of low image editing performance and reduce attribute editing ability, etc., and achieve the effect of improving attribute reshaping and attribute editing ability, and improving image editing performance.

Pending Publication Date: 2022-05-13
ZHEJIANG DAHUA TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current way of editing attributes of images will reduce the ability to edit attributes, making image editing performance low

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 editing method, training method of image editing model, equipment and device
  • Image editing method, training method of image editing model, equipment and device
  • Image editing method, training method of image editing model, equipment and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0027] The terms "first" and "second" in this application are only used for descriptive purposes, and should not be understood as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of these features. In the description of the present application, "plurality" means at least two, such as ...

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 editing method, an image editing model training method, equipment and a device. The method comprises the following steps: acquiring a plurality of coding features of different dimensions of a target image, wherein the target image comprises an attribute tag; generating bidirectional information by using the coding features and the attribute tags; wherein the bidirectional information comprises a forward information sequence and a reverse information sequence, the forward information sequence is generated by using the coding features and the attribute tags of the first dimension sequence, and the reverse information sequence is generated by using the coding features and the attribute tags of the second dimension sequence; one of the first dimension sequence and the second dimension sequence is from high dimension to low dimension, and the other one is from low dimension to high dimension; and decoding based on the plurality of coding features and the bidirectional information to obtain an edited target editing image. According to the scheme, the image editing performance can be improved.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to an image editing method, an image editing model training method, computer equipment and a storage device. Background technique [0002] With the development of computer technology, the application scenarios of image editing technology are becoming more and more extensive. For example, many application software of the terminal device have the function of image editing, usually a large number of image editing functions are integrated on the terminal device, and the user can edit different attributes of the image through different image editing functions, so as to realize the effect of attribute editing of the image. However, the current method of editing attributes of an image will reduce the ability to edit attributes, resulting in low image editing performance. Contents of the invention [0003] The technical problem mainly solved by this application is to p...

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): G06T11/60G06T9/00G06K9/62G06V10/774G06V10/80
CPCG06T11/60G06T9/00G06F18/253G06F18/214
Inventor 顾晓炜
Owner ZHEJIANG DAHUA TECH CO LTD
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