Image super-resolution reconstruction method based on multi-scale pyramid network

A technology of super-resolution reconstruction and image resolution, applied in image analysis, image enhancement, image data processing and other directions, can solve the problems of gradient disappearance, grid degradation, and the quality of high-resolution images needs to be improved, and achieve high image quality. , feature-rich effects

Inactive Publication Date: 2020-07-10
SOUTH CHINA UNIV OF TECH +1
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current mainstream methods are based on the theory that the deeper the network, the better the reconstruction effect. With the increase of the network depth, problems such as gradient di

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 based on multi-scale pyramid network
  • Image super-resolution reconstruction method based on multi-scale pyramid network
  • Image super-resolution reconstruction method based on multi-scale pyramid network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0041] Such as figure 1 As shown, this embodiment provides an image super-resolution reconstruction method based on a multi-scale pyramid network. Through the multi-scale residual module, the extracted features are fused and strengthened, and the pyramid network is used for progressive upsampling to gradually reconstruct the image. , including the following steps:

[0042] S1. Perform shallow feature extraction on the input image, specifically:

[0043] Using a 3×3 convolutional layer followed by a nonlinear activation unit, shallow features are extracted from the input low-resolution image, expressed as follows:

[0044] f 0 =σ(W 1 *I LR ) (1)

[0045] Among them, I LR Represents the input low-resolution image, σ represents the nonlinear activation function ReLU, W 1Represents the convolution kernel of the 3×3 convolutional layer, F 0 Represents features extracted by convolutional layers.

[0046] S2. Perform feature fusion and feature enhancement on shallow features...

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 an image super-resolution reconstruction method based on a multi-scale pyramid network. The image super-resolution reconstruction method comprises the following steps of S1, performing shallow feature extraction on an input image; S2, performing feature fusion and feature enhancement on the shallow features through K multi-scale residual modules to obtain richer deep features; S3, performing up-sampling on the deep features by using transposed convolution; S4, reconstructing the image by using residual learning; and S5, taking the reconstructed image as the output of the current pyramid network and the input of the next layer of pyramid network, and continuing to adopt the steps S1-S4 for training, so as to obtain an image with higher resolution. According to the method, a multi-scale residual module is adopted to fuse features to obtain richer features; meanwhile, a Laplacian pyramid network is adopted to gradually upsample and reconstruct a high-resolution image; and by means of the method, images with richer details and higher quality can be reconstructed.

Description

technical field [0001] The invention relates to the technical fields of computer vision and image processing, in particular to an image super-resolution reconstruction method based on a multi-scale pyramid network. Background technique [0002] With the development of information technology, the number of pictures on the Internet is constantly increasing. As a main medium for people to perceive the world, images have been applied to various scenarios. In many fields, as large as the field of medical images, satellite remote sensing, as small as people's cameras, mobile phones, etc. People have higher and higher requirements for image quality. Therefore, improving the resolution of images will be of great significance in real life. [0003] Image super-resolution reconstruction aims to restore high-resolution images from one or more low-resolution images, and has become one of the research hotspots in the field of computer vision in recent years. At present, super-resoluti...

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): G06T3/40G06T5/50G06T7/50G06N3/04G06N3/08
CPCG06T3/4076G06T3/4007G06T7/50G06T5/50G06N3/08G06N3/045
Inventor 史景伦杨鹏梁可弘陈学斌林阳城
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products