Method, device, and apparatus for three-dimensional face reconstruction, and compute readable storage medium

A three-dimensional face and target face technology, applied in computer parts, calculation, 3D modeling, etc., can solve the problems of high image quality limitation and complex deformation technology calculation, so as to improve the reconstruction quality, overcome the complex operation, The effect of high-precision 3D face reconstruction

Inactive Publication Date: 2018-11-27
上饶市中科院云计算中心大数据研究院
View PDF6 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this warping technique is computationally complex and has high limitations on image quality

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
  • Method, device, and apparatus for three-dimensional face reconstruction, and compute readable storage medium
  • Method, device, and apparatus for three-dimensional face reconstruction, and compute readable storage medium
  • Method, device, and apparatus for three-dimensional face reconstruction, and compute readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0053] figure 1 For the three-dimensional face reconstruction method provided in the first embodiment of the present invention, the three-dimensional face reconstruction method includes:

[0054] Step 101, obtaining a face reference image set of a target face, the face reference image set including at least two face reference images;

[0055] Step 102, perform facial feature point calibration on each of the face reference images in the human face reference image set, each of the face reference images is marked with q feature points, and q is a positive integer greater than or equal to 1 ;

[0056] Step 103: Perform global contour deformation on the reference model based on the calibrated feature point pixel coordinates to obtain an initial face model after global contour deformation, and the reference model is a known 3D face model;

[0057] Step 104, performing photometric normal reconstruction on the primary face model using normal-based photometric stereo technology to ob...

no. 2 example

[0093] figure 2 For the three-dimensional face reconstruction method provided in the second embodiment of the present invention, the three-dimensional face reconstruction method includes:

[0094] Step 201. Obtain three face reference image sets of the target face, which are the frontal neutral image set (A), the deflected 30-degree neutral image set (B) and the frontal random expression image set (C), such as image 3 shown.

[0095] Specifically, compile the dlib library, which is a c++ library that contains many commonly used algorithms for machine learning. Download the face reference image of LDiCaprio, which can contain face images of front, side, multi-expression, and different lighting, and divide the image into Three face reference image sets, namely the frontal neutral image set (A), the 30-degree deflected neutral image set (B) and the frontal random expression image set (C). And each face reference image set contains 40 images, of which the frontal neutral image...

no. 3 example

[0103] The present invention also provides a three-dimensional face reconstruction device, which includes:

[0104] The first module is used to obtain a human face reference image set of a target human face, and the human face reference image set includes at least two human face reference images;

[0105] The second module is used to perform facial feature point calibration on each of the human face reference images in the human face reference image set, and each of the human face reference images is marked with q feature points, and q is greater than or equal to 1 a positive integer;

[0106] The third module is used to perform global contour deformation on the reference model based on the calibrated feature point pixel coordinates to obtain an initial face model after global contour deformation, and the reference model is a known three-dimensional face model;

[0107] The fourth module is used to perform photometric normal reconstruction on the primary face model using norm...

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 method, a device, and an apparatus for three-dimensional face reconstruction, and a compute readable storage medium. The method comprises: marking feature points of a face reference image in a face reference image set, performing global contour deformation on a reference model based on pixel coordinates of the feature points, and performing photometric normal reconstruction on a deformed primary face model by a photometric stereo technology based on a normal, based on a surface normal vector of the reconstructed target face model, using a mesh deforming technology toiterate to generate a target face model by the optimized normal. The invention provides a robust three-dimensional face reconstruction technology based on the photometric normal, with help of unrestrained image sets and reference models, and combined with the photometric stereo technology and a mesh deformation technology, restriction on face reference images is reduced, and advantages of the twotechnologies are used. The method prevents defects of using one technology alone to reconstruct faces, improves quality of three-dimensional face reconstruction, and realizes robust three-dimensionalface reconstruction with high accuracy.

Description

technical field [0001] The present invention relates to the field of electronic technology, and more specifically, to a three-dimensional face reconstruction method, device, equipment and computer-readable storage medium. Background technique [0002] Image-based 3D face reconstruction is widely used in face recognition, public security, medical treatment, game animation, film and television entertainment and other fields. It aims to realize the reconstruction of 3D geometric model of human face. And challenging research hotspots. At present, 3D face reconstruction techniques are mainly divided into two categories: active reconstruction techniques and passive reconstruction techniques. Active reconstruction technology uses a 3D depth scanner to capture the 3D position information of the face, and constructs a 3D model of the face after fitting. Depth scanner-based methods can obtain accurate results, but require special hardware devices and high costs, so they are not suit...

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): G06T17/00G06K9/00
CPCG06T17/00G06V40/168
Inventor 皮慧婷洪学海李小畅陈鑫
Owner 上饶市中科院云计算中心大数据研究院
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap