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

Face image super-resolution method and system

A face image and super-resolution technology, which is applied in the field of computer vision and image processing, can solve the problems that the effect of image super-resolution needs to be further improved, and achieve the effect of promoting learning

Pending Publication Date: 2021-11-09
SHANGHAI JIAO TONG UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the image super-resolution effect of this patent needs to be further improved, especially when the input image is severely damaged.

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 super-resolution method and system
  • Face image super-resolution method and system
  • Face image super-resolution method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention. Parts that are not described in detail below can be implemented using existing technologies.

[0036] Such as figure 1 As shown, it is a flow chart of a method for super-resolution of a face image based on a pre-trained generative model according to an embodiment of the present invention.

[0037] Please refer to figure 1 , the face image super-resolution method based on the pre-training generation model of the present embodiment includes:

[0038] S11: For the input face attribute label informat...

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 super-resolution method and system, and the method comprises the steps: carrying out the feature optimization of input face attribute tag information through a full-connection network and an activation layer, and obtaining attribute semantic features; extracting visual features of the input low-resolution image information by using a convolutional neural network; performing feature fusion on the attribute semantic features and the visual features by using a feature fusion network, and constraining the attribute semantic features and the visual features with teacher features through attribute normal vectors during training so as to keep the fusion features consistent with the teacher feature attributes; and mapping the fusion feature into an output image by using an image recovery network, wherein because the image recovery network is pre-trained, the image generated by the image recovery network has vivid details. According to the invention, the generated face high-definition image has attribute maintenance and details.

Description

technical field [0001] The invention relates to a method in the fields of computer vision and image processing, in particular to a method and system for super-resolution of human face images. Background technique [0002] Face super-resolution aims to improve the resolution of face images, and generates a corresponding high-resolution face image (HR) from a low-resolution face image (LR). In the past few years, many super-resolution methods based on deep neural networks have achieved great success. However, super-resolution is a pathological problem. Multiple high-resolution images can be degraded into the same low-resolution image, that is, one low-resolution image corresponds to multiple high-resolution images. During training, the network is also affected by this one-to-many relationship, fitting a low-resolution image corresponding to the average of multiple high-resolution images, which leads to blurred output images. With this in mind, some methods use pre-trained ge...

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): G06T3/40G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06T3/4053G06N3/08G06T2207/20081G06T2207/30201G06N3/045G06F18/253Y02T10/40
Inventor 张娅姜文波赵贵华张小云董洋轶张毅军王延峰蔺飞袁旭稚
Owner SHANGHAI JIAO TONG 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