Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

3D face reconstruction method based on convolutional neural network model

A technology of convolutional neural network and 3D face, applied in biological neural network model, neural learning method, neural architecture, etc., can solve the problems of high reconstruction cost, long reconstruction time, poor reconstruction effect, etc., and achieve low reconstruction cost , the reconstruction effect is stable, and the reconstruction time is short

Inactive Publication Date: 2018-02-09
CHANGSHA UNIVERSITY
View PDF3 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of the above defects or improvement needs of the prior art, the present invention provides a 3D face reconstruction method and system based on a convolutional neural network model. Technical issues such as poor quality, long rebuilding time, and high rebuilding cost

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
  • 3D face reconstruction method based on convolutional neural network model
  • 3D face reconstruction method based on convolutional neural network model
  • 3D face reconstruction method based on convolutional neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] 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.

[0041] Such as Figure 5 As shown, the three-dimensional face reconstruction method based on the convolutional neural network model of the present invention comprises the following steps:

[0042] (1) Obtain the input sample data set;

[0043] Specifically, the way to obtain the input sample data set in this step includes directly downloading pictures from the Internet as the input sample data...

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 a 3D face reconstruction method based on a convolutional neural network model. The method includes the following steps: acquiring an input sample data set; taking a single 2D image in the input sample data set as input based on a 3D MM algorithm and a convolutional neural network model, and outputting the 3D model parameters of the 2D image; repeating the steps for the remaining 2D images in the input sample data set to get the 3D model parameters corresponding to all the 2D images, selecting the 3D model parameters corresponding to different 2D images of the same individual in all the 2D images, and aggregating the 3D model parameters according to the degree of confidence to get the 3D model structures of all individuals; and training the convolutional neural network model with the input sample data set as input and the 3D model parameters of all individuals as output, in order to get a final 3D face reconstruction model. The technical problem that the existing3D face reconstruction method has the disadvantages of poor reconstruction effect, long reconstruction time and high reconstruction cost is solved.

Description

technical field [0001] The invention belongs to the technical field of image processing and deep learning, and more specifically relates to a three-dimensional face reconstruction method based on a convolutional neural network model. Background technique [0002] 3D face reconstruction has been widely used in medical, education, entertainment and other fields. However, there are two main technical problems in the current application of 3D face reconstruction in real scenes: first, the effect of 3D face reconstruction is not good, mainly reflected in the unstable 3D simulation, which leads to large differences in the 3D simulation of the same individual; Secondly, 3D face reconstruction takes a long time and costs high. Contents of the invention [0003] In view of the above defects or improvement needs of the prior art, the present invention provides a method and system for 3D face reconstruction based on a convolutional neural network model. technical issues such as poo...

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): G06T17/00G06N3/04G06N3/08
CPCG06N3/08G06T17/00G06N3/045
Inventor 李方敏彭小兵刘新华陈柯栾悉道
Owner CHANGSHA UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products