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

Single-image super-resolution reconstruction method based on hierarchical progressive network

A layer-progressive image reconstruction technology, applied in the field of image super-resolution, can solve the problems of poor reconstruction effect and difficult one-time completion, so as to avoid gradient disappearance and improve transmission efficiency

Active Publication Date: 2019-07-23
NANJING UNIV OF SCI & TECH
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for super-resolution reconstruction of a single image, which overcomes the problems of the existing methods such as poor reconstruction effect under high-magnification super-resolution tasks, difficulty in completing multi-scale super-resolution tasks at one time, etc.

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
  • Single-image super-resolution reconstruction method based on hierarchical progressive network
  • Single-image super-resolution reconstruction method based on hierarchical progressive network
  • Single-image super-resolution reconstruction method based on hierarchical progressive network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The solutions of the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0033] Such as figure 1 Shown is the hierarchical progressive network structure diagram of the present invention for single image super-resolution. The hierarchical progressive neural network proposed by the present invention can perform super-resolution processing on a single picture with a reconstruction factor of s (wherein, s=2 or 4 or 8). The network consists of a set of cascaded upsampling units, each tasked with super-resolution of images by a factor of 2. Each level of upsampling unit structure mainly includes feature extraction branch and image reconstruction branch.

[0034] Among them, the feature extraction branch in each level of upsampling unit structure is as follows: figure 2 shown. Including feature extraction convolution layer, nonlinear mapping module, upsampling layer.

[0035] The feature extraction l...

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 provides a single-image super-resolution reconstruction method based on a hierarchical progressive network. The single-image super-resolution reconstruction method mainly comprises a feature extraction branch, an image reconstruction branch, a hierarchical progressive network structure and a loss function. According to the method, a high-power super-resolution task is decomposed intoa plurality of sub-tasks, each sub-task can be independently completed by one super-resolution unit network, and the plurality of super-resolution unit networks are cascaded to form the whole network. According to the invention, the same training model can be used to carry out multiple times of super-resolution reconstruction processing on the image.

Description

technical field [0001] The invention relates to the technical field of image super-resolution, in particular to a single-image super-resolution reconstruction method based on a hierarchical progressive network. Background technique [0002] Image super-resolution refers to the technology of recovering corresponding high-resolution images with more detailed information by using a single low-resolution image or a sequence of low-resolution images with sub-pixel offsets on the basis of the original hardware equipment conditions. The restored image can express latent details and hidden structures, and the visual effect of the image is enhanced. Image super-resolution technology has played an important role in medical imaging, security monitoring, audio-visual entertainment, satellite remote sensing and other fields. [0003] At present, the most widely used single-image super-resolution reconstruction techniques are learning-based methods, including methods based on over-comple...

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): G06T3/40G06N3/04
CPCG06T3/4053G06T3/4007G06N3/045
Inventor 王清华孙浩洋
Owner NANJING UNIV OF SCI & TECH
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