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

Virtual face generation method

A face and face feature technology, applied in the field of virtual face generation, to achieve the effect of reducing costs

Pending Publication Date: 2021-12-10
WUHAN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The invention provides a method for generating a virtual human face, which can generate a personalized human face animation with smooth and natural lip movements and rich and realistic facial expression changes by using speech text and real person image information, which solves the existing problems The technology needs to rely on a large number of training samples to ensure the technical problem of face generation effect

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
  • Virtual face generation method
  • Virtual face generation method
  • Virtual face generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] Aiming at the existing technical problems, the present invention takes Chinese as the research object, and designs a virtual human face generation method driven by Chinese text and emotional vocabulary. Based on the key frame interpolation face animation model, the Chinese phoneme-viseme-key frame mapping is established, and the mouth frame driven by the Chinese pinyin phoneme is designed; at the same time, the emotion keyword detection method based on the basic emotion dictionary is used to drive the face of the virtual character Facial facial expression changes, to achieve a lip-sync virtual face that can simultaneously take into account changes in mouth shape, expression changes, and image personalization.

[0061] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the ...

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 virtual face generation method, which takes Chinese as a research object, and utilizes a speaking text, a front face image of a real person and side face image information to generate a lip-tone-synchronized personalized face animation with smooth and natural mouth shape actions and rich and vivid facial expression changes. The method comprises: original face geometric modeling, face dynamic mouth shape modeling, face facial expression modeling, voice modeling and virtual face synthesis. The invention provides a set of complete virtual human face manufacturing steps, the manufacturing cost is low, and the lip sound synchronous virtual human face which can give consideration to mouth shape change, expression change and image individuation at the same time can be realized. The method has wide application value and development prospect in many fields such as film production, computer games, virtual anchors, virtual customer service, online virtual teacher teaching and the like.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence virtual human application, in particular to a method for generating a virtual human face. Background technique [0002] In recent years, with the continuous development of computer vision, computer graphics, and artificial intelligence technology, virtual humans have begun to be used in various industries, such as virtual hosts, virtual teachers, etc. The emergence of these applications has put forward higher requirements for generating virtual faces. Virtual face generation aims to produce personalized face animation with smooth and natural mouth movements and lip-sound synchronization with rich and realistic facial expression changes. It is widely used in film production, computer games, virtual anchors, virtual customer service, and online virtual teacher teaching. And many other fields have broad application value and development prospects. Taking online virtual teacher teach...

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): G06T13/40G06T13/20G11B27/10G06F40/289G06F40/216
CPCG06T13/40G06T13/205G11B27/10G06F40/289G06F40/216
Inventor 谢榕江路遥
Owner WUHAN UNIV
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