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

Resolution-by-resolution improved image super-resolution restoration method based on an attention mechanism

A super-resolution and attention technology, applied in image analysis, image enhancement, image data processing and other directions, can solve problems such as inability to handle multi-scale problems

Pending Publication Date: 2020-07-28
BEIJING UNIV OF TECH
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such methods have a disadvantage: they cannot handle multi-scale problems in a single framework

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
  • Resolution-by-resolution improved image super-resolution restoration method based on an attention mechanism
  • Resolution-by-resolution improved image super-resolution restoration method based on an attention mechanism
  • Resolution-by-resolution improved image super-resolution restoration method based on an attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0034] The overall structure of the present invention is as figure 1 shown. A low-resolution image of 480×480 is obtained after downsampling using bicubic linear interpolation. Input low-resolution images into the designed network consisting of convolutional layers and residual blocks to learn the mapping relationship. First, the network model uses a 3×3 deformable convolution for feature extraction of information. The activation unit is RELU, which is used to reduce the interdependence of parameters and solve the occurrence of overfitting problems. Then, four iterative basic block units are designed, and the feature dimensions are 64, 128, and 512 respectively. The block unit is mainly composed of two deformable convolutions and SElayer operations, which can be more conducive to extracting the edge features of the target. Finally, shuffle is use...

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 resolution-by-resolution improved image super-resolution restoration method based on an attention mechanism, which is mainly based on a resolution-by-resolution improved super-resolution restoration network of a double attention mechanism, and improves the feature extraction capability of a model by introducing a convolution module of a feature dimension attention mechanism and a spatial dimension attention mechanism. Furthermore, related ideas of a resolution-by-resolution improvement network in the field of adversarial neural networks are used for reference, the network learning difficulty is simplified, and super-resolution restoration of resolution-by-resolution improvement is realized. Finally, the algorithm performance is tested through a DIV2K data set, andexperimental results show that the method can improve the input low-resolution image resolution by resolution, the same network can improve the resolution by 2-4 times at the same time, and the PSNRvalue of the reconstructed image is significantly superior to that of a current mainstream algorithm.

Description

technical field [0001] The present invention belongs to the research hotspot of super-resolution restoration in the field of image processing. It is a method of using a double attention mechanism to upgrade the super-resolution restoration network by resolution to obtain a single-frame image with higher resolution, which is different from the current mainstream Based on the convolutional neural network of SRCNN, VDSR and SRResNet, this method improves the feature extraction ability of the model; simplifies the difficulty of network learning, and realizes super-resolution restoration with resolution-by-resolution improvement; it has been well verified on public datasets. Background technique [0002] The super-resolution restoration of images, especially the super-resolution restoration of single-frame images, has received more and more attention and research in recent years. Its goal is to reconstruct a high-resolution image from a single low-resolution image. Typically, th...

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): G06T3/40G06T5/00G06N3/04G06N3/08
CPCG06T3/4076G06N3/08G06T2207/20081G06T2207/20084G06N3/045G06T5/00
Inventor 王素玉张雨婷
Owner BEIJING UNIV OF 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