A product image rapid generation method based on a series confrontation network

A technology for image generation and pattern generation, applied in 2D image generation, image data processing, biological neural network models, etc., can solve the problems of large gaps in texture block structure, support user input texture block training complexity, etc., to achieve texture structure resolution and color effects

Active Publication Date: 2019-06-04
ZHEJIANG UNIV OF TECH
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The second is that the training of the invention that supports user input texture blocks is complex, and the texture structure of the generated image is quite different from the texture block structure input by the user.

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
  • A product image rapid generation method based on a series confrontation network
  • A product image rapid generation method based on a series confrontation network
  • A product image rapid generation method based on a series confrontation network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] Example: The product image generation process is divided into two stages. The first stage is to generate a complete black and white image with black and white texture pattern blocks and sketch outlines. The style of this black and white image is the same as the black and white image after adaptive threshold binarization. The second stage is to use the black-and-white image and color scheme generated in the first stage to generate a color image. In design, the designer's input is divided into two parts: sketch outline and texture block. The entire image generation process goes through two generation models, one is the black and white texture pattern generation model (GuessPattern Generator), and the other is the image generation model (PaintGANGenerator). The input of the black-and-white texture pattern generation model has two parts, which are the black-and-white sketch outline and the black-and-white texture pattern of the color texture block binarized by adaptive thr...

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 relates to a product image rapid generation method based on a series confrontation network. According to the method, texture structure reasoning and color reasoning are realized by usingtwo models respectively; And the whole network structure is formed through series connection, and product image generation is completed through a discriminant function. According to the network structure, the complexity of the problem is decomposed, the training difficulty is reduced, and the generation effect is improved.

Description

technical field [0001] The invention relates to the technical field of generating digital images, in particular to a method for quickly generating product images based on a serial confrontation network. Background technique [0002] In computer-aided design, the existing commercial software basically provides the rendering and display function of realistic graphics, so that designers can check whether the appearance of their designed products meets the needs of customers. However, for designers, building a geometric model of the desired scene is complex and time-consuming. At present, there are many commercial 3D modeling software, such as Autodesk's 3DMax, Maya, and AutoCAD, which are all geometric modeling tools developed for professionals. They both require the designer to gradually build a model of the scene from very detailed and well-defined geometry. The core of these modeling tools is to precisely define the three-dimensional coordinates of each detailed component ...

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): G06T11/00G06N3/04
Inventor 郑河荣罗永文
Owner ZHEJIANG 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap