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

Method for generating image based on multi-target sketch of progressive adversarial generation network

A technology for generating images and multi-objectives, which is applied in the directions of image conversion, image analysis, image enhancement, etc., can solve problems such as errors in synthesis results, and achieve the effect of promoting the overall image and promoting the generation

Active Publication Date: 2019-08-09
DALIAN UNIV OF TECH
View PDF2 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, using text descriptions to retrieve images in the network is strongly dependent on the label information of the image. If the image label in the network is inconsistent with the image, it will directly lead to an error in the final synthesis result.

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
  • Method for generating image based on multi-target sketch of progressive adversarial generation network
  • Method for generating image based on multi-target sketch of progressive adversarial generation network
  • Method for generating image based on multi-target sketch of progressive adversarial generation network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0076] In this embodiment, XShell, Xftp terminal emulator and Jupyter notebook interactive interface are used on the server of GTX Titan X and 12G graphics card, and the relatively stable deep learning framework tensorflow-GPU version 1.8.0 is used, and the cuda version is 9.0 .176. Using the progressive confrontation generation network proposed by the present invention, combined with the sketch image pair obtained by the sketch discriminative amplification technique, the entire process of generating images from multi-object sketches is completed.

[0077] In this embodiment, 21 categories of MS-COCO image data (including background) are collected. These image categories overlap with the image categories in the Pascal VOC dataset. In order to unify the input of the network, these 20 categories (not included) will be obtained. The image containing the background) is cropped to obtain a size of size=256*256. The instance images of different categories are obtained through the 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 present invention provides a method for generating image based on multi-target sketch of a progressive adversarial generation network, which promotes generation of instance texture colors and promotes generation of overall image relationships by decoupling instances from the generation process of the whole image, and provides a multi-target sketch generation method based on a progressive adversarial generation network. A discriminant sketch amplification technology is used, and the sketch information of the discriminant area is acquired, so that the image generation process has more accurate structure constraint. The method provided by the invention solves the problem that the existing network neglects the distribution of instance parts in the image due to learning of the distributionof the whole image and thus generates the same texture and color on different instances. In an MS-COCO data set, the relatively high Inception Score and the relatively low Fre'chet inception distanceare obtained. The method obtains a very good result in the aspects of quality and diversity of the generated data.

Description

technical field [0001] The invention belongs to the field of computer image generation, and relates to a method for generating images based on multi-target sketches of a progressive confrontation generation network. Background technique [0002] The painting design process involves a lot of creative work. The process usually starts with sketches on paper, whereby designers and engineers share their ideas and use the sketches as a basis to create a work of art that can reproduce the real scene. Images depicting the real world often contain multiple object instances, thus image generation from sketches with multiple instances is an attractive research topic. In the past, in the field of multi-object sketch generation images, using the feature information of each sketch to perform cross-domain retrieval was the focus of research. The reference images obtained by retrieval were used to replace the instance objects in the sketches, and then a synthetic real image was obtained by...

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): G06T3/00G06T7/13
CPCG06T7/13G06T2207/20084G06T2207/20081G06T3/04
Inventor 王智慧王宁李建军窦智李豪杰罗钟铉
Owner DALIAN UNIV OF TECH
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