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

Face restoration method based on generative adversarial network

A repair method and generative technology, applied in the field of deep learning and image processing, can solve the problems of mode collapse, unstable network training, and low similarity, and achieve the effect of solving instability.

Inactive Publication Date: 2019-09-10
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 41 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] There are two technical problems to be solved by the present invention: one is that the existing generative confrontation network has problems of unstable network training and mode collapse; the other is that the existing face repair images do not conform to visual cognition and the similarity is not high

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 restoration method based on generative adversarial network
  • Face restoration method based on generative adversarial network
  • Face restoration method based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0031] The present invention provides a face image restoration method based on a generative confrontation network, on the basis of using a generative confrontation network to generate a visually compliant face image, by introducing the context loss related to the face image with missing information and the missing information Adversarial loss, and together with the global and local discriminative loss as the loss function, while using the encoding-decoding network as the generation network to retain the missing image information, through iterating the network model, finally obtain the context loss requirements and meet the visual cognition The image is generated, and finally the corresponding part of this raw image is used to achieve effective face image inpainting.

[0032] Such as figure 1 As shown, a kind of face restoration method based o...

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 face restoration method based on a generative adversarial network. The method comprises the following steps: S1, collecting face data and preprocessing the face data; s2, establishing an adversarial network model, wherein the adversarial network model comprises two deep neural networks: a generation network G and a discrimination network D, and generating a face image through the generation network G; judging whether the image is true or false through the judgment network D; and S3, performing face restoration: randomly adding a mask to the test image, simulating a real image defect area, inputting the defect image into a generation network G to generate a face image, replacing the mask area of the generated image with a corresponding position of a missing image,and performing Poisson fusion. Parameters of the network are iteratively updated by utilizing context loss and context loss and global and local discrimination loss, and more natural and realistic face images can be generated and complemented.

Description

technical field [0001] The invention belongs to the technical field of deep learning and image processing, in particular to a face restoration method based on a generative confrontation network. Background technique [0002] Image inpainting technology is an important branch in the field of image processing in recent years, which belongs to the interdisciplinary problems of pattern recognition, machine learning, statistics, computer vision and so on. Image restoration refers to the repair and reconstruction of the missing image information caused by the image preservation process or the repair after removing redundant objects in the image. Nowadays, researchers have proposed a variety of image restoration methods, which have been widely used in the fields of old photo restoration, cultural relic protection, and removal of redundant objects. [0003] At present, digital image restoration algorithms mainly include three directions: structure-based image restoration algorithms...

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): G06K9/00G06K9/62G06N3/04
CPCG06V40/172G06N3/045G06F18/214
Inventor 吴立军陈灿林
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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