Human face super-resolution method guided by the reference image based on three-dimensional deformation model

A three-dimensional deformation and super-resolution technology, applied in the field of face super-resolution, which can solve problems such as performance degradation

Active Publication Date: 2021-01-15
TIANJIN UNIV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the expressions and poses of the reference image and the low-resolution image are very different, the performance of such methods will drop significantly.

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
  • Human face super-resolution method guided by the reference image based on three-dimensional deformation model
  • Human face super-resolution method guided by the reference image based on three-dimensional deformation model
  • Human face super-resolution method guided by the reference image based on three-dimensional deformation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The technical scheme adopted in the present invention is a face super-resolution method guided by a reference image based on a three-dimensional deformation model, and the general idea of ​​the method is as follows:

[0050] First take the reference image I R Deformation based on the 3D deformation model, so that the deformed reference image with low resolution image I L With the same expression and gesture. There are two repair methods in the deformation process: the symmetry of the face is used to fill the texture of the invisible area before deformation, and the two operations are used to eliminate the artifacts after filling. The reference image after warping and low resolution image I L As the input of the super-resolution network, the high-resolution face image I is output after the super-resolution network H . Specifically, the content of each step is as follows:

[0051] 1) Deformation based on a three-dimensional deformation model specifically refers t...

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 relates to low-resolution human face super-resolution, provides a super-resolution algorithm for solving the problem that expressions and postures of a reference image and a low-resolution human face image are greatly different, and discloses a human face super-resolution method guided by the reference image based on a three-dimensional deformation model. The method comprises the following steps of: firstly, deforming a reference image IR based on a three-dimensional deformation model; filling textures of an invisible area before deformation by utilizing the symmetry of a human face; eliminating artifacts after filling by using two operations at the same time; and taking the deformed reference image and the low-resolution image IL as the input of the super-resolution network,and outputting a high-resolution face image IH after passing through the super-resolution network. The invention is mainly applied to face recognition occasions.

Description

technical field [0001] The invention belongs to the field of computer vision and relates to super-resolution of human faces with very low resolution. Specifically, in modern society, a person usually has multiple photos of different times, different expressions, and different postures. The present invention uses any one of the high-resolution photos to guide the low-resolution face of the same person after being deformed by a three-dimensional deformation model. The reconstruction of the face, that is, the face super-resolution algorithm guided by the reference map based on the 3D deformation model. Background technique [0002] Face super-resolution is to restore a high-resolution face image from a low-resolution input. Since many tasks require high-resolution face images, such as face alignment, face recognition, etc. Therefore, it is necessary to study face super-resolution. Dealing with very low resolutions has always been a huge challenge. At this stage, face super-...

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): G06T3/40G06K9/00G06T5/50
CPCG06T3/4053G06T5/50G06T2207/10024G06T2207/10012G06V40/174G06V40/168
Inventor 岳焕景姜中玉杨敬钰侯永宏
Owner TIANJIN UNIV
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