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

Image super-resolution reconstruction method, system and computer storage medium

A super-resolution reconstruction and super-resolution technology, applied in the field of image super-resolution reconstruction methods, systems and computer storage media, can solve the problem of insufficient detail information on the edge of the face and so on.

Active Publication Date: 2022-04-29
WUHAN INSTITUTE OF TECHNOLOGY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The image generated by the face has a good visual subjective effect, but the details of the edge of the face are not obvious enough

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
  • Image super-resolution reconstruction method, system and computer storage medium
  • Image super-resolution reconstruction method, system and computer storage medium
  • Image super-resolution reconstruction method, system and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The principles and features of the present invention are described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0057] The present invention provides an image super-resolution reconstruction method, system and computer storage medium, which uses a generation network and a discriminant network to perform edge-enhanced super-resolution reconstruction, and generates an adversarial network based on edge enhancement composed of a generative network and a discriminant network. structure diagram ( figure 2 ), define k to represent the size of the convolution kernel, n to represent the number of filters, and s to represent the step size. In the experimental data set with sample size N, the low-resolution image set and the original high-res image set Denote the trained LR and the corresponding HR respectively, and define G(X) to ...

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 relates to an image super-resolution reconstruction method, system and computer storage medium. The method includes the following steps, S1, reshaping the original image into an image of a fixed size to obtain the original high-resolution image, and converting the original high-resolution The image is interpolated and down-sampled to obtain a low-resolution image; S2, based on the generation network, performs super-resolution reconstruction based on edge enhancement on the low-resolution image to obtain a super-resolution image; S3, based on the discriminative network and the original high-resolution image pair Super-resolution images for authenticity discrimination. In the present invention, a single low-resolution image is expressed through enhanced edge detail information, and an edge enhancement fusion network is added to the original super-resolution reconstruction generation network to improve image super-resolution reconstruction performance and obtain a clearer reconstructed image; in addition, the discriminant network It can also improve the reconstruction performance of edge-enhanced generative adversarial networks.

Description

technical field [0001] The present invention relates to the technical field of image super-resolution, in particular to an image super-resolution reconstruction method, system and computer storage medium. Background technique [0002] Face super-resolution reconstruction is based on the idea of ​​image super-resolution reconstruction, combined with the lateral image super-resolution reconstruction algorithm generated by the structural features in the face image, to achieve low-resolution ( Low-Resolution, LR) face image can restore and restore the technology of high-resolution (High-Resolution, HR) face image with rich information. Face super-resolution technology can improve the resolution and clarity of face images, so that the limited face information in the original very low-resolution images can be expressed in more detail, and it plays an important role in applications such as security and criminal investigation. effect. [0003] Dong et al. brought the image super-r...

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): G06T3/40G06T5/50
CPCG06T3/4053G06T3/4046G06T5/50G06T2207/20081G06T2207/20084G06T2207/20221G06T2207/20192G06T2207/30201
Inventor 卢涛陈冲张彦铎许若波周强郝晓慧魏博识郎秀娟王宇吴志豪王彬
Owner WUHAN INSTITUTE OF TECHNOLOGY
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