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

Neural network design and training method for denoising lightweight real image

A neural network and real image technology, applied in neural learning methods, biological neural network models, image enhancement, etc., can solve problems such as simulation, many neural network parameters, and unfavorable neural network training

Active Publication Date: 2021-07-30
XI AN JIAOTONG UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In real scenarios, the use of neural networks for image denoising is mainly limited by two aspects: after terminal digital image processing, the noise types will become more complex, which is difficult to simulate in the experimental environment, which is not conducive to neural network training; common neural network There are many parameters, it is difficult to meet the real-time operation on the mobile terminal

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
  • Neural network design and training method for denoising lightweight real image
  • Neural network design and training method for denoising lightweight real image
  • Neural network design and training method for denoising lightweight real image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Below in conjunction with accompanying drawing, the present invention is described in further detail:

[0039] 1. The present invention designs a denoising network combined with a second-order residual attention module

[0040] The present invention designs a novel real image denoising network structure combined with a second-order residual attention module. The denoising network adopts a 4-scale U-shaped network structure, and the overall structure of the network is as follows: figure 1 shown.

[0041] The denoising network consists of 7 second-order residual blocks (2ndRB) and 3 wavelet downsampling layers and 3 wavelet upsampling layers in total. Name 2ndRB as 2ndRB according to the distance from the input 1 ...2nd RB 7 . For the input noisy image, first go through 2ndRB 1 Extract features, 2ndRB 1 The output of has two branches: the first branch is passed to the back of the network, and the 2ndRB 6 The outputs are summed and input to 2ndRB 7 Middle; the sec...

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 neural network design and training method for denoising lightweight real image, the lightweight real image denoising neural network adopts a four-scale U-shaped network structure, and comprises seven second-order residual attention modules, three down-sampling modules and three up-sampling modules. According to the method, the real noisy image can be quickly denoised, and the denoised image is obtained.

Description

technical field [0001] The invention relates to the field of real image denoising, in particular to a neural network design and training method for lightweight real image denoising. Background technique [0002] The rise of neural networks has greatly advanced the task of Gaussian image denoising. Because Gaussian noise is easy to simulate, it can be directly added to the image to obtain the data set required by the neural network. The reorganized data set brings the stable Gaussian noise denoising effect of the neural network. In real scenarios, the use of neural networks for image denoising is mainly limited by two aspects: after terminal digital image processing, the noise types will become more complex, which is difficult to simulate in the experimental environment, which is not conducive to neural network training; common neural network There are many parameters, it is difficult to meet the real-time operation on the mobile terminal. Therefore, it is of high academic ...

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
IPC IPC(8): G06T5/00G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06T2207/20064G06T2207/20081G06V10/44G06N3/045G06T5/70
Inventor 侯兴松刘恒岳
Owner XI AN JIAOTONG 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