Face image restoration method based on face style

A face image and style technology, applied in the field of image restoration, can solve problems such as facial semantic inconsistency, visual artifacts, and blurred facial structure details, and achieve the effects of making up for obvious boundary connections, real images, and solving blurred facial area repairs

Active Publication Date: 2021-08-24
HEBEI UNIV OF TECH +1
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention can effectively overcome the problems of visual artifacts, blurred facial structure details and inconsistent facial semantics in the repaired face images of the prior art, and obtain more accurate repairing effects

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
  • Face image restoration method based on face style
  • Face image restoration method based on face style
  • Face image restoration method based on face style

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0141] The face image restoration method based on the generative confrontation network of the present embodiment adopts the adaptive fusion mechanism of the local facial region style and the global facial pattern and the region normalized facial region restoration module, and the specific steps of the generation network based on the facial pattern are as follows:

[0142] In the first step, the facial style extraction sub-network is used to extract the local facial area styles and global facial styles of the damaged face image to form a style matrix:

[0143]In step (1.1), the damaged face image is extracted through the facial style extraction sub-network to extract the deep style features of the damaged face image, and the specific operation is shown in the following formula (1):

[0144] f s =StyleExtractNet(I in ) (1),

[0145] In formula (1), I in is the damaged face image, F s is the deep style feature of the damaged face image, StyleExtractNet( ) is the facial style ...

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 a face image restoration method based on a face pattern, and the method comprises the following steps: constructing a face pattern-based generative adversarial network which comprises a face pattern-based generative network and a PatchGAN discriminator network; wherein the face pattern-based generative network comprises a trunk repair sub-network formed by an encoder and a decoder, and a face pattern extraction sub-network capable of extracting a local face region pattern and a global face pattern of each face region according to a face analysis graph; wherein all the local face area styles and the global face styles form a style matrix, and affine parameters of all the face areas are generated; and hopping connections exist between corresponding network layers in the encoder and the decoder, and a face area restoration module is embedded in each hopping connection. The problems of visual artifacts, fuzzy facial structure details and inconsistent facial semantics in the repaired face image in the prior art can be effectively solved, and a more accurate repairing effect is obtained.

Description

technical field [0001] The technical solution of the present invention relates to the field of image restoration, in particular to a face image restoration method based on facial style. Background technique [0002] Image restoration (image completion or image filling) is a technology to infer and repair the content of damaged or missing areas based on known image content, so that the repaired image content information is reasonable and subjectively visually true. In recent years, with the rapid development of deep learning, image restoration has also made great progress, and is widely used in the fields of object removal, image restoration of damaged cultural relics, film and television post-processing, and old photo restoration. [0003] Existing image inpainting methods can be divided into two categories, namely image inpainting based on traditional methods and image inpainting based on deep learning methods. The former is mainly based on low-level features such as the c...

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): G06T5/00G06N3/04G06N3/08
CPCG06T5/005G06N3/08G06T2207/20081G06T2207/20221G06T2207/30201G06N3/045
Inventor 阎刚李文鑫朱叶郭迎春于洋高理想张帅青
Owner HEBEI UNIV OF TECH
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