Three-dimensional human face reconstruction method and system based on two-step shape modeling

A three-dimensional face and three-dimensional human technology, applied in the field of three-dimensional face modeling, can solve the problem of impossible depth information, and achieve the effects of strong application value, high modeling accuracy and simple calculation.

Inactive Publication Date: 2009-04-08
CHONGQING UNIV OF POSTS & TELECOMM
View PDF2 Cites 62 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the case of only one photo as input, it is usually impossible ...

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
  • Three-dimensional human face reconstruction method and system based on two-step shape modeling
  • Three-dimensional human face reconstruction method and system based on two-step shape modeling
  • Three-dimensional human face reconstruction method and system based on two-step shape modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] The present invention proposes to use the face shape statistical model as a tool to build a three-dimensional face reconstruction system, and use the spatial distribution knowledge of the corresponding feature points on the face model in the face database to estimate the depth value of the feature points of the specific face on the photo . According to this idea, the present invention proposes a two-step facial shape modeling (Two-stepFacial Shape Modeling, TSFSM) scheme-first establishes the sparse statistical model of the training library according to the facial feature points, and then uses the optimization algorithm to estimate the test facial features The depth value of the face feature, and the known two-dimensional coordinates and the estimated depth value are combined to obtain the quasi-3D (Quasi-3D, Q-3D) coordinates of the feature points (it is called a quasi-three-dimensional coordinate because the real three-dimensional coordinate value is unknown); then, t...

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 for carrying out the three-dimensional human face modeling by a single human face photo to obtain a realistic human face, and the method belongs to the field of graphics and images. The method utilizes a priori knowledge of a human face structure to estimate the depths of two-dimensional feature points on the photo, thereby obtaining similar three-dimensional coordinates; the similar three-dimensional feature points are taken as control points, and the dirichlet free deformation algorithm is adopted to realize the fitting of the neutral human face to the specific human face. Then, a method which is based on the regional expansion is adopted to realize the texture synthesis and the mapping, and the region which is not covered is repaired by adopting the interpolation or the block filling method. The method has simple calculation, high modeling accuracy and can rapidly utilize a small number of feature points to realize the three-dimensional modeling of the human face on the single photo, and the generated three-dimensional human face model has very strong realistic feeling under various postures due to the accurate estimation of the depths of the feature points. The method can also be used for the three-dimensional reconstruction of other objects.

Description

technical field [0001] The invention relates to the fields of computer graphics, digital image processing, artificial intelligence and the like, in particular to a method and system for three-dimensional human face modeling through plane images. Background technique [0002] The existing 3D face modeling technology can be roughly divided into two methods based on hardware (3D scanner, structured light, etc.) and image-based modeling. Accurate face models can be obtained by using 3D digital scanners to obtain 3D face information. However, due to the high cost and inflexibility of hardware equipment, it is generally only suitable for some special occasions. Therefore, the method of facial personality modeling based on information in images or videos has a huge market prospect. [0003] Through the retrieval of technical literature in recent years, it can be found that the representative image-based face modeling method is to calculate and restore the three-dimensional informa...

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): G06T17/00G06T15/10
Inventor 王国胤龚勋
Owner CHONGQING UNIV OF POSTS & TELECOMM
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