A Human Body Geometry Reconstruction Method Based on Euler Field Deformation Constraints

A human body and deformation technology, applied in the field of geometric reconstruction of the human body based on Euler field deformation constraints, can solve problems such as complex limitations, achieve the effects of improving computing efficiency, increasing computing speed, and ensuring reconstruction quality

Active Publication Date: 2022-04-05
杭州同绘科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to carry out the structural reconstruction of the 3D human body, the general method is to establish the human body shape space or perform internal anatomical simulation, which are relatively complex and have certain limitations

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
  • A Human Body Geometry Reconstruction Method Based on Euler Field Deformation Constraints
  • A Human Body Geometry Reconstruction Method Based on Euler Field Deformation Constraints
  • A Human Body Geometry Reconstruction Method Based on Euler Field Deformation Constraints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] figure 1 The overall processing flow of the human body geometric reconstruction based on the Euler field deformation constraint is provided, and the present invention is further described below in conjunction with the accompanying drawings.

[0051] The present invention provides a human body geometry reconstruction method based on Euler field deformation constraints, specifically skeleton deformation driven by feature points, local deformation driven by HRBF and shape deformation driven by Euler field, comprising the following steps:

[0052] (1) Rough alignment of human body posture based on feature point-driven skeleton deformation: using the target human body grid as the data source, using the random forest regression method to extract predefined human body feature points, and then calculating the target human body skeleton nodes through these feature points; The feature points drive the skeleton deformation, and use the Linear Blend Skinning (LBS) method to first o...

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 human body geometry reconstruction method based on Euler field deformation constraints, comprising the following steps: taking a target human body grid as a data source, extracting human body feature points by using a random forest regression method, and calculating to obtain a target human body skeleton node; Point-driven skeleton deformation, using LBS method to drive mesh deformation, so that the template model and the target model pose roughly aligned; based on the local field generated by HRBF, perform rigid transformation driven by local shape difference; perform regional expansion based on local shape driving and shrinkage; based on SDF, optimize the target energy function in the Euler field based on target data constraints, human body deformation constraints, and level set characteristic constraints, calculate the deformation vector field to obtain the SDF deformation result, and drive the template grid and target accordingly. The shape of the model is aligned to achieve human reconstruction. The invention improves the robustness and efficiency of the three-dimensional human body structural reconstruction, and satisfies the needs of human body reconstruction for rough data.

Description

technical field [0001] The invention specifically relates to a human body geometry reconstruction method based on Euler field deformation constraints. Background technique [0002] In recent years, the 3D modeling of objects in virtual scenes, especially the 3D modeling of human bodies, can not only be applied to character creation required in film and television, games, etc., but also has a wide range of applications in virtual fitting, medical assistance, vocational education, etc. However, the method of human body modeling has certain limitations, and there are still some difficulties and cumbersome calculations for accurate, rapid and realistic reconstruction of a specific human body model. In recent years, 3D human body reconstruction that meets the requirements of engineering and scientific research has attracted the attention of scholars and scientific research institutions at home and abroad. The research on 3D human body reconstruction based on computer graphics-re...

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 Patents(China)
IPC IPC(8): G06T17/20
CPCG06T17/20
Inventor 郝爱民李帅梁晓辉杨文军高阳
Owner 杭州同绘科技有限公司
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