Three-dimensional hair parameterization model method based on body vector field sparse localization decomposition

A parametric model, vector field technology, applied in 3D modeling, image data processing, computer parts and other directions, can solve problems such as time-consuming and laborious

Active Publication Date: 2020-07-28
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] There are relatively few studies on the direction of manual interactive editing, because it is time-consuming and laborious and requires users to have a certain grasp of hair art, but it has the advantages of high degree of freedom of operation and fine modeling 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
  • Three-dimensional hair parameterization model method based on body vector field sparse localization decomposition
  • Three-dimensional hair parameterization model method based on body vector field sparse localization decomposition
  • Three-dimensional hair parameterization model method based on body vector field sparse localization decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further described below in conjunction with specific examples.

[0062] Such as figure 1 As shown, the 3D hair parametric model method based on the sparse localized decomposition of the volume vector field provided in this embodiment includes the following steps:

[0063] 1) For the 3D hairstyle database {H containing 343 data i} Carry out the preprocessing from the node-hairline structure to the volume vector field conversion, including the following steps:

[0064] 1.1) If figure 2 As shown in , a global compact AABB bounding box is calculated first, and the lengths of its three sides are respectively calculated from the extreme values ​​of the database on the x, y, and z axes.

[0065] 1.2) Voxelize the bounding box and specify the voxelization scale S vox , take the subdivision data of the shortest side among the three sides of the bounding box as S vox , the number of subdivisions on the other two sides is based on the length rat...

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 three-dimensional hair parameterization model method based on body vector field sparse localization decomposition, and the method comprises the steps: 1) carrying out the preprocessing of converting hair style data from a node-hair structure to a body vector field, and obtaining the information of hair length and local density; 2) calculating average data of a body vectorfield, a hair length and a local density, and constructing three residual matrixes for dimension reduction processing; 3) performing dimension reduction processing on the three residual matrixes by using SPLOC to obtain sparse localization bases of three features, and performing linear mixing on the sparse localization bases and respective average data to obtain a parameterized model; and 4) assigning different mixing coefficients to the parameterized model, and calculating hair nodes from the body vector field by using a hair reconstruction method based on an Euler broken line method to obtain different new hair style data. According to the invention, a simple three-dimensional hair style manual editing function is realized, so that a user can reconstruct abundant and diverse three-dimensional hair models by simply selecting different feature bases and adjusting the mixing coefficient of the feature bases.

Description

technical field [0001] The invention relates to the technical field of computer graphics and three-dimensional hairstyle data reconstruction, in particular to a three-dimensional hair parametric model method based on sparse localized decomposition of volume vector field. Background technique [0002] Hair modeling has a wide range of application backgrounds in the fields of film and television entertainment, virtual reality, etc., but 3D hair modeling is still in the immature exploration stage, and it is a research difficulty in computer graphics. A hairstyle has as many as thousands of hair strands , hairstyles have no rules to follow, and 3D hairstyle data is difficult to obtain. Various reasons make the research of 3D hair modeling full of challenges. In recent years, the research on hair modeling at home and abroad has gradually become hot, and it shows different research directions. At present, the main methods of hair modeling are divided into two categories: manual in...

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): G06T17/00G06K9/62
CPCG06T17/00G06T2210/12G06F18/2135
Inventor 梁君达李桂清
Owner SOUTH CHINA UNIV OF TECH
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