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

Three-dimensional model deformation algorithm based on quasi-conformal mapping

A three-dimensional model, conformal mapping technology, applied in the field of computer vision, can solve problems such as difficult deformation, poor model processing effect, and rotation sensitivity.

Active Publication Date: 2019-08-27
ZHONGBEI UNIV
View PDF21 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the problems existing in the existing 3D model deformation algorithm mentioned above, and in order to solve the utilization rate of the existing model, the existing deformation algorithm needs to operate more control points. Due to the poor processing effect of the inconspicuous model and the sensitivity of differential coordinate deformation technology to rotation, and the difficulty of directly deforming the three-dimensional model, the present invention proposes a three-dimensional model deformation algorithm based on quasi-conformal mapping. 3D model deformation of images, suitable for deformation of models with any boundaries

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 model deformation algorithm based on quasi-conformal mapping
  • Three-dimensional model deformation algorithm based on quasi-conformal mapping
  • Three-dimensional model deformation algorithm based on quasi-conformal mapping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] Such as figure 1 As shown, a 3D model deformation algorithm based on quasi-conformal mapping, which includes the following steps:

[0073] Step 1, such as figure 2 As shown, the input two-dimensional face image is preprocessed, and the contour line of the object in the image and the feature point set {t:} are extracted. The extracted contour line is as follows image 3 shown; where the feature point set {t:} is obtained by preprocessing the target image, extracting the information of the contour and feature points, and the extraction of feature points is as follows Figure 4 shown.

[0074] Step 2, use the 3D model retrieval method to find the model with the highest similarity with the target image face in the MeshDGP 3D model library as the deformed 3D source model, and obtain the information of the number of vertices and the number of faces of the retrieved model, which are respectively recorded as V n ={v 1 , v 2 , v 3 ,...,v n}, f m ={f 1 , f 2 , f 3 ,.....

Embodiment 2

[0107] The difference between embodiment 2 and embodiment 1 is:

[0108] The target 2D image is a 2D ear image, and the retrieved 3D source model is an ear model, such as Figure 8 Shown are the renderings of the 2D ear mesh model and the 2D plane disc parameterized by the 3D source model, where the left picture is the rendering of the 2D ear grid model parameterized to the 2D plane disc, and the right picture is Rendering of the parameterization of the 3D source model of the ear to a 2D planar disk. Select 3 vertices in the earring part as control points, and perform stretching and translation operations. The two-dimensional model before and after deformation is as follows: Figure 9 shown, where Figure 9 (a) is the two-dimensional image before deformation, Figure 9 (b) is the deformed two-dimensional image, and the final three-dimensional model result image obtained by deforming the ear model is as follows Figure 10 shown. ε=0.001 in step 6.3, m=200 in step 7.3.

Embodiment 3

[0110] The difference between embodiment 3 and embodiment 1 is:

[0111] The target 2D image is a 2D wrinkled old man image, and the retrieved 3D source model is a wrinkled old man model, such as Figure 11 Shown is the rendering of the 2D folded elderly mesh model and the 2D plane disk parameterized by the 3D source model, where Figure 11 (a) is the effect diagram of parametrizing the 2D folded elderly mesh model to a 2D plane disc, Figure 11 (b) The rendering of the parameterization of the 3D source model of the wrinkled old man to the 2D flat disk. Select a vertex in the wrinkled old man's lips as a control point to make the mouth corners of the model open. The two-dimensional model before and after deformation is as follows: Figure 12 shown in , where Figure 12 (a) is the two-dimensional image before deformation, Figure 12 (b) is the deformed two-dimensional image, and the final three-dimensional model result image obtained by deformation of the wrinkled elderly m...

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 belongs to the field of computer vision, and discloses a three-dimensional model deformation algorithm based on quasi-conformal mapping. The method comprises the following steps of firstly, parameterizing a three-dimensional model to a two-dimensional plane disc by utilizing the quasi-conformal mapping, secondly, adopting a quasi-common iterative algorithm to calculate the mapping between the two planes, and obtaining a deformed two-dimensional model, and finally, restoring the deformed two-dimensional model into a three-dimensional model meeting constraint conditions as much aspossible by adopting a 2D-to-3D model restoration algorithm. According to the present invention, the problems that an existing model is low in utilization rate, the number of control points needing tobe operated by a deformation algorithm is large, the model processing effect on skeletons is poor, the differential coordinate deformation technology is sensitive to rotation, and the direct deformation on a three-dimensional model is difficult, are solved. Compared with a traditional mapping method, the method is simple, and keeps more local details of the source mode. The method is suitable forthe three-dimensional model deformation based on a single image, and is suitable for the deformation of a model with any boundary. The method can be applied to the fields of animation, cosmetic surgery, medicine, geometric modeling and the like.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a three-dimensional model deformation algorithm based on quasi-conformal mapping. Background technique [0002] Vision is an important means for human beings to perceive and understand the world. Computer vision technology allows computers to acquire, process, analyze and identify images by simulating human vision to realize the understanding of the real world. The deformation of 3D models has always been one of the research hotspots in the field of computer vision, and can be widely used in fields such as film and television, animation, virtual fitting, virtual reality, video games, medicine, and rapid construction of 3D models. Through the deformation of the 3D model, the 3D model of the target image can be obtained. Secondly, the model can be edited to obtain other effects, and a complete 3D model can be quickly constructed to make it more effective and ap...

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): G06T19/20G06F16/583
CPCG06T19/20G06T2219/2021G06F16/583
Inventor 常敏况立群常伟候瑞环牛昊杰常婷
Owner ZHONGBEI 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