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

Establishing method of human face 3D model by fusing multiple-visual angle and multiple-thread 2D information

A two-dimensional information and three-dimensional model technology, which is applied in the processing of 3D images, the generation of 2D images, and image data processing, etc., can solve the problems of inaccurate models and insufficient models

Inactive Publication Date: 2003-03-19
TSINGHUA UNIV
View PDF0 Cites 55 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method utilizes multi-view information, it only uses the corresponding two-dimensional point information on multiple images and does not make full use of other shape constraints, and the obtained model is not accurate enough, especially in areas where the texture is not rich.
[0004] These methods have some common disadvantages: (1) the model is not fine enough; (2) cannot do MPEG4 (moving picture compression coding organization standard 4) compatible animation

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
  • Establishing method of human face 3D model by fusing multiple-visual angle and multiple-thread 2D information
  • Establishing method of human face 3D model by fusing multiple-visual angle and multiple-thread 2D information
  • Establishing method of human face 3D model by fusing multiple-visual angle and multiple-thread 2D information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0129] We create the face model under a general model specific framework, namely: from the general model Face g At the beginning, it is gradually modified according to the obtained two-dimensional information of the modeling object, and finally the specific person model Face is obtained. s . In this process, only the three-dimensional point coordinates in P are modified, and F remains unchanged, that is, the topology is constant (P and F together represent the shape model of the face, that is, Face={P, F}. Specifically Ground, P={M pti =(X pti Y pti Z pti ) T |pti=1,...,nVertex} is a list of three-dimensional nodes on the face, and F={facet fj =(pt 1，fj pt 2，fj pt 3，fj ) T |fj=1,...,nMesh} is a list of triangle faces on the face, where each facet fj =(pt 1，fj ,pt 2，fj pt 3，fj ) T represented by three points in P M pt 1 , fj , ...

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 belongs to the field of computer-aided human face image re-construction technology. The present invention features that human face as model establishing object is first photographed with two, one upper and one lower, stere ovideo cameras to obtain video sequence from the front to the side of the face with unchanged expression; the precise posture parameters in different times are then obtained via autoamtic posture estimating algorithm; after the initiation of model and posture, 3D information are extracted separately from two types of 2D threads including one stereo reconstruction type of the image and the other matching and correcting type of model projection contour and image contour; and the 3D face model is finally established.

Description

technical field [0001] The invention relates to a method for establishing a three-dimensional face model which combines multi-view and multi-cue two-dimensional information and belongs to the technical field of computer face image reconstruction. Background technique [0002] Existing methods for creating 3D face models from images lack strategies to extract 3D information from multiple 2D clues and fuse them. Kang, Sing Bing and others proposed a semi-automatic method of creating a face model based on a single frontal image in the patented technology of "image method and apparatus for semi-automatically mapping a face on to a wireframe topology" (United States Patent 6,031,539) method. The principle of this method is to automatically detect multiple feature points on the face image, and then locate the landmark points of the face according to the feature points, and then obtain the coordinates of all grid points in the face wireframe model accordingly. displacement to cre...

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): G06T11/00G06T15/70
Inventor 徐光祐张辉
Owner TSINGHUA 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