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

A method for automatically generating hyper-realistic 3D facial models based on machine learning

An automatic generation and machine learning technology, applied in the field of computer vision, can solve the problem of high cost of 3D face modeling, and achieve the effect of simplifying the generation steps and cost

Active Publication Date: 2021-03-09
江苏原力数字科技股份有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for automatically generating a super-realistic 3D facial model based on machine learning, so as to solve the problem that the existing 3D face modeling is often costly and requires people to go to the scene for scanning

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
  • A method for automatically generating hyper-realistic 3D facial models based on machine learning
  • A method for automatically generating hyper-realistic 3D facial models based on machine learning
  • A method for automatically generating hyper-realistic 3D facial models based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Such as figure 1 As shown, the method for automatically generating a super-realistic 3D facial model based on machine learning comprises the following steps:

[0042] S1, using the 3DMM three-dimensional deformation model to fit the 2D face image into a 3D face model;

[0043] S2, using a deep learning neural network to generate a UV map;

[0044] S3. Applying the UV map to the 3D face model to generate a super-realistic 3D face model.

[0045] Such as figure 2 As shown, using the 3DMM three-dimensional deformation model to fit the 2D face image into a 3D face model, including the following steps:

[0046] S101. The linear expression for constructing a 3D face model is:

[0047]

[0048] in, represents the average face model, Represents the face shape part, Represents the facial expression part, Indicates the face shape factor, Indicates the facial expression coefficient;

[0049] S102, obtain a 2D face picture, adopt the dlib library to detect and ob...

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 present invention provides a method for automatically generating a super-realistic 3D face model based on machine learning, comprising the following steps: S1, using a 3DMM three-dimensional deformation model to fit a 2D face picture into a 3D face model; S2, using a deep learning neural network to generate UV map; S3, applying the UV map to the 3D face model to generate a super-realistic 3D face model; based on a 2D face picture, a super-realistic 3D face model can be generated without other equipment and steps, greatly The generation steps and costs are simplified.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a method for automatically generating a super-realistic 3D facial model based on machine learning. Background technique [0002] With the development of computer graphics technology, 3D face modeling and 3D face models with expressions and actions have become a research hotspot in the field of computer graphics. 3D face modeling and 3D face models with expressions and actions have been gradually promoted and applied to many fields such as virtual reality, film and television production, face recognition, game entertainment, etc., and have strong application value. [0003] The method that the three-dimensional human face model generation with expression action is at present is: the static human face three-dimensional model (specifically with reference to CN106164979A) obtained by structured light three-dimensional imaging equipment, then utilizes animation pro...

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 Patents(China)
IPC IPC(8): G06T17/00G06T3/00G06N3/08G06N3/04G06K9/00
CPCG06T17/00G06T3/0006G06N3/08G06V40/168G06V40/174G06N3/045
Inventor 赵锐侯志迎
Owner 江苏原力数字科技股份有限公司
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