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

Generative adversarial network-based grayscale picture colorizing method

A colorization and network technology, applied in the field of deep learning and image generation, can solve the problems of easy loss of details and complex operation of images

Active Publication Date: 2018-10-26
BEIJING INSTITUTE OF GRAPHIC COMMUNICATION
View PDF6 Cites 66 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For those who are not familiar with Photoshop, such an operation is very complicated, and the image is prone to loss of detail

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
  • Generative adversarial network-based grayscale picture colorizing method
  • Generative adversarial network-based grayscale picture colorizing method
  • Generative adversarial network-based grayscale picture colorizing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] The picture generation method combining DiscoGAN, Progressive Growing GAN, WGAN and CGAN is explained in detail below in conjunction with the accompanying drawings.

[0067] The grayscale image colorization system of the present invention should include the following parts: sample data collection, sample image preprocessing, generation of adversarial network model establishment, network training and testing and adjusting hyperparameters. The main steps included in the present invention are: collecting pictures and performing preprocessing, inputting the pictures into the generative confrontation network, training the survival confrontation network, adjusting the hyperparameters of the generative confrontation network and repeated training to obtain the final model, such as figure 1 shown. Its system structure is as figure 2 shown. The sample data collection link is responsible for collecting enough grayscale and color pictures that contain rich detailed information a...

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 generative adversarial network-based grayscale picture colorizing method. A DiscoGAN, a Progressive Growing GAN, a Wasserstein GAN and a CGAN are combined to generate a generative adversarial network. The method comprises the following steps of: firstly collecting and arranging picture samples and dividing the samples into two groups, wherein one group comprises N grayscale pictures and the other group comprises N color pictures; designing architecture of the generative adversarial network to ensure that the trained network can generate pictures with high resolutionsand high quality; transmitting the samples into the generative adversarial network to start training, and after the generative adversarial network is stably trained, enhancing the resolutions of generated pictures by using a PGGAN. According to the method, WGAN-PG is added in the network to improve the original generative adversarial network, so that the problems of gradient instability and mode collapse are solved, and the process of optimizing the generative adversarial network is improved. Finally, a description limiting function of the CGAN is added in the network, so that pictures with appointed styles can be generated according to descriptions.

Description

technical field [0001] The invention relates to a colorization method of a grayscale image combining DiscoGAN, PGGAN, CGAN and WGAN, and belongs to the technical field of deep learning and image generation. Background technique [0002] With the development of computer hardware and neural networks, artificial intelligence has gradually gained people's attention, and it is also playing an increasingly important role in people's lives. Deep learning originated from the development of neural networks. Its concept was proposed by Hinton et al. in 2006. Its purpose is to simulate the human brain to analyze and interpret data. People hope to find a deep neural network model through deep learning, which can represent the probability distribution among various data encountered in artificial intelligence applications, such as image processing, natural language processing, etc. One of the most impressive achievements in deep learning so far is the discriminative model, which can take...

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): G06T3/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06T3/04
Inventor 解凯何翊卿何南南李天聪李桐
Owner BEIJING INSTITUTE OF GRAPHIC COMMUNICATION
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