Unlock instant, AI-driven research and patent intelligence for your innovation.

Network model training method, face image super-resolution reconstruction method and equipment

A technology for super-resolution reconstruction and training images, which is applied in the field of image processing and can solve problems such as poor visual perception of images.

Pending Publication Date: 2021-03-16
ZHEJIANG DAHUA TECH CO LTD
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above methods usually perform well on indicators such as PSNR (Peak Signal-to-Noise Ratio) (Peak Signal-to-Noise Ratio), but the actual generated image has poor visual perception

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
  • Network model training method, face image super-resolution reconstruction method and equipment
  • Network model training method, face image super-resolution reconstruction method and equipment
  • Network model training method, face image super-resolution reconstruction method and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0037] This application proposes a network model training method, which can be applied to super-resolution face image reconstruction of low-resolution face images, aiming at generating low-resolution face images into super-resolution face images, Through the training method of the network model of this application, the clarity of the image generated by the network model can be improved. For details, please refer to figure 1 , figure 1 It is a schem...

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 training method of a network model, and a face image super-resolution reconstruction method and device. The network model training method comprises the following steps: acquiring a low-resolution training image and a high-resolution training image corresponding to the low-resolution training image, and acquiring the low-resolution training image and the high-resolution training image based on shooting of the same target object; inputting the low-resolution training image into a generation network to obtain a super-resolution training image, and calculating error loss of the super-resolution training image and the high-resolution training image; inputting the high-resolution training image and the super-resolution training image into a discrimination network to obtain the adversarial loss of the high-resolution training image and the super-resolution training image; and training the network model based on the error loss and the adversarial loss until the sum ofthe error loss and the adversarial loss output by the trained network model is smaller than a first preset loss threshold. According to the scheme, the definition of the image generated by the networkmodel is improved.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to a method for training a network model, a method and equipment for super-resolution reconstruction of face images. Background technique [0002] As an important technology in the field of image processing and computer, image super-resolution aims to convert low-resolution images into high-resolution images. At present, more and more experts and scholars have introduced deep learning into the field of image super-resolution, using SRCNN (Super-Resolution Convolutional Neural Network) combined with traditional difference methods and convolutional neural networks to perform super-resolution on low-resolution images. processed to obtain super-resolution images. The above methods usually perform well on indicators such as PSNR (Peak Signal-to-Noise Ratio) (Peak Signal-to-Noise Ratio), but the actual generated image has poor visual perception. Contents of the inven...

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): G06T3/40
CPCG06T3/4053G06T3/4046
Inventor 惠强
Owner ZHEJIANG DAHUA TECH CO LTD