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

Manifold constraint and FB-GAN combined face deformation method and system

A FB-GAN, face deformation technology, applied in the field of face image deformation, can solve problems such as unreal images, and achieve the effect of improving authenticity

Pending Publication Date: 2022-03-22
WUHAN INSTITUTE OF TECHNOLOGY +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the images generated by this method often contain various artifacts and appear unreal, and traditional gradient-based algorithms are usually based on human prior knowledge

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
  • Manifold constraint and FB-GAN combined face deformation method and system
  • Manifold constraint and FB-GAN combined face deformation method and system
  • Manifold constraint and FB-GAN combined face deformation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.

[0060] Embodiments of the present invention include an image stitching module, a human face fusion network, and a human face deformation model; the image stitching module is used to paste the open mouth part in the target face image to the source face image to replace the source face image The closed mouth in the middle; the face fusion network is used to obtain a high-resolution fusion image co...

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

According to the manifold constraint and FB-GAN combined face deformation method and system provided by the invention, an end-to-end face image splicing adversarial network FB-GAN is designed by using a generative adversarial neural network, and a function of generating a high-resolution face image in a face deformation process is realized. According to the method, the high-resolution face image is generated through the face deformation algorithm, and the problem of mouth distortion or void caused by the fact that the mouth of the human face is opened from closing in traditional deformation is solved. According to the invention, the problem of poor splicing effect caused by large color difference in the face splicing problem is solved, and the authenticity of the face generated image is improved.

Description

technical field [0001] The invention belongs to the technical field of face image deformation, and in particular relates to a face deformation method and system combining manifold constraints and FB-GAN. Background technique [0002] The goal of image deformation is to deform the object into the desired shape and posture, usually based on a set of different handles controlled by the user, where the control handles generally include points, lines or polygonal meshes. Scheafer et al. proposed a rigid image deformation algorithm based on moving least squares (Moving Least Squares, MLS) constructed by feature points. The algorithm constructs a deformation function through a linear function (such as rigid transformation). The rigid deformation algorithm based on MLS makes The deformation is "as rigid as possible", which can better maintain the global shape and local details of the target. This algorithm can be better applied to the deformation of rigid objects (such as changing ...

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): G06T5/50G06T3/40G06V40/16G06V10/82G06N3/04G06N3/08
CPCG06T5/50G06T3/4038G06N3/08G06T2207/30201G06T2207/20221G06T2207/20132G06T2200/32G06N3/045
Inventor 周华兵徐志超王燕燕张彦铎卢涛陈灯鲁统伟李晓林李迅朱锐
Owner WUHAN INSTITUTE OF TECHNOLOGY
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