Unlock instant, AI-driven research and patent intelligence for your innovation.

A Face Image Inpainting Method Based on Facial Style

A face image and style technology, applied in the field of image restoration, can solve the problems of visual artifacts, inconsistent facial semantics, blurred facial structure details, etc., to achieve the effect of real image, make up for obvious boundary connection, and solve blurred facial area restoration

Active Publication Date: 2022-03-04
HEBEI UNIV OF TECH +1
View PDF9 Cites 0 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
  • A Face Image Inpainting Method Based on Facial Style
  • A Face Image Inpainting Method Based on Facial Style
  • A Face Image Inpainting Method Based on Facial 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 present invention is a kind of method based on the face image restoration of face pattern, and this method comprises the following content: Build the generation confrontation network based on face pattern, comprise the generation network based on face pattern and PatchGAN discriminator network; Based on the generation network of face pattern Including the backbone repair sub-network composed of encoder-decoder, the facial style extraction sub-network that can extract the local facial area style and global facial style of each facial area according to the face analysis map; all local facial area styles and global facial styles form a style matrix to generate the affine parameters of each facial region; there are skip connections between the encoder and the corresponding network layers in the decoder, and each skip connection is embedded with a facial region restoration module. This method can effectively overcome the problems of visual artifacts, blurred facial structure details, and inconsistency of facial semantics in the repaired face image of the prior art, and obtain a more accurate repair effect.

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 Patents(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