Supercharge Your Innovation With Domain-Expert AI Agents!

Fast 3D Face Reconstruction Method Based on Compressed Sensing Theory

A 3D face and compressed sensing technology, applied in the field of image processing, can solve the problems of reconstruction result deviation, failure to consider the reconstruction result, impact, etc., and achieve the effect of reducing reconstruction time, improving reconstruction efficiency, and improving reconstruction accuracy

Active Publication Date: 2016-08-10
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The difference between different facial shapes may be very large, and the current 3D face reconstruction method is generally based on the idea of ​​linear class, which treats all face samples as the same class, and does not take into account the samples in the training sample library and the test data. The possible impact of sample variability on the reconstruction results
For face test samples, if there are multiple training samples with large differences in shape in the sample library, it will obviously lead to deviations in the reconstruction results

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
  • Fast 3D Face Reconstruction Method Based on Compressed Sensing Theory
  • Fast 3D Face Reconstruction Method Based on Compressed Sensing Theory
  • Fast 3D Face Reconstruction Method Based on Compressed Sensing Theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Below in conjunction with accompanying drawing, the technical scheme of invention is described in detail:

[0026] like figure 1 As shown, the 3D face reconstruction method based on compressive sensing theory includes the following steps.

[0027] Step 1: Initialize the 3D face sample library, build a 2D face sample library, and collect 2D image feature points for calibration: the standardization of the 3D face sample library is to realize the correction of the face pose in the sample library, the 3D face point set Resampling and point correspondence; the two-dimensional sample library can be obtained from the three-dimensional face sample library according to the method of orthogonal projection; the calibration of the input two-dimensional image feature points can be manually calibrated or automatically determined, and the two-dimensional facial feature points Corresponding feature points exist in the three-dimensional model.

[0028] Assuming that the two-dimensiona...

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 face rapid reconstruction method based on compressed sensing theory, and belongs to the technical field of image processing. The reconstruction method introduces compressed sensing theory into the linear combination of samples, screens out training samples that are highly similar to test samples, streamlines the sample library, speeds up reconstruction and improves reconstruction accuracy through reconstruction on similar samples.

Description

technical field [0001] The invention discloses a three-dimensional human face fast reconstruction method based on compressed sensing theory, which belongs to the technical field of image processing. Background technique [0002] In recent years, due to the continuous development of pattern recognition and computer vision technology, face-based applications have gradually emerged. With the gradual commercialization of applications such as face detection and face recognition, people have realized that people expressed in two-dimensional pictures Face information is generally constrained by conditions such as illumination and pose in actual processing. Therefore, the research on human face has gradually shifted from two-dimensional plane to three-dimensional space. As the preprocessing part of 3D face data, the acquisition of traditional 3D information usually adopts direct scanning, which requires expensive hardware conditions and the close cooperation of participants. The 3...

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): G06T17/00G06K9/62
CPCH04N25/00
Inventor 周大可吴子扬杨欣曹元鹏方三勇
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com