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

A human face intrinsic image decomposition method based on skin color priori

A face image and intrinsic image technology, which is applied in the field of face intrinsic image decomposition based on skin color prior, can solve problems such as complex acquisition equipment, residual ambient light, and inability to correctly identify skin color, so as to ensure normal skin color and facilitate rendering effect

Active Publication Date: 2019-06-18
ZHEJIANG UNIV
View PDF15 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The traditional facial intrinsic image acquisition method requires complicated acquisition equipment
However, the eigendecomposition method for a single face image is not ideal, mainly due to the inability to correctly identify the skin color, and it is prone to problems such as ambient light residues.

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 face intrinsic image decomposition method based on skin color priori
  • A human face intrinsic image decomposition method based on skin color priori
  • A human face intrinsic image decomposition method based on skin color priori

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] The present invention will be described in detail below according to the accompanying drawings.

[0014] The present invention is based on the human face eigenimage decomposition method of skin color prior, comprises the following steps:

[0015] Step 1: Perform 3D reconstruction and face feature point recognition on the input face image, calculate the face depth map according to the reconstructed 3D model, divide the face area according to the face feature points, and divide the face into 9 different parts. Area;

[0016] (1.1) 3D reconstruction and facial feature point recognition adopt the displaced dynamic expression method (Cao Chen. An image-based dynamic substitute construction method [P]. Chinese patent: CN106023288A, 2016-10-12), A total of 90 face feature points were extracted.

[0017] (1.2) According to the 3D reconstructed 3D model, use the depth buffer during rendering to export the depth information to generate a corresponding height map.

[0018] (1.3...

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 face intrinsic image decomposition method based on skin color priori, which can extract a human face reflectivity intrinsic image from a single human face photo. The method comprises the following three steps of: in a preprocessing stage, carrying out three-dimensional reconstruction on a human face, extracting human face feature points at the same time, and then carrying out human face region division; In the highlight separation stage, positioning and removing highlight by utilizing a light intensity ratio; And in the intrinsic separation stage, solving a reflection intrinsic graph by using an optimization method in combination with priori such as smoothness and face skin color priori. The input required by the method is only a single picture, and the generated reflectivity intrinsic graph can better retain the skin color information.

Description

technical field [0001] The present invention relates to the field of computer graphics, in particular to a human face intrinsic image decomposition (Intrinsic Image Decomposition) method based on skin color prior. Background technique [0002] With the rapid development of virtual reality and augmented reality technology, how to use computers to quickly and accurately model and render the 3D world has become a topic of constant discussion in academia and industry. As an essential part of it, the human face has also received extensive attention and research. Making a 2D face photo into a 3D face model mainly includes two processes: 3D reconstruction and texture editing. The 3D reconstruction process restores the face picture to a 3D geometric structure, and the texture editing process makes the face picture a texture map of the 3D model. Using the 3D model and its texture, combined with related rendering algorithms, the face can be rendered in real time, re-illuminated and ...

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): G06T7/50G06T7/90G06T17/00G06K9/00
Inventor 石育金任重
Owner ZHEJIANG 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