Contour enhancement method for approximately simulating chapping in style conversion

A contour enhancement and style technology, applied in the field of computer vision, can solve the problem that the effect of style conversion needs to be further improved

Pending Publication Date: 2022-04-22
NORTHWEST UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies in the existing technology, the purpose of the present invention is to provide a contour enhancement method that approximates the texture method in style transfer, so as to solve the technical problem that the effect of style conversion from landscape photos to landscape paintings needs to be further improved in the prior art

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
  • Contour enhancement method for approximately simulating chapping in style conversion
  • Contour enhancement method for approximately simulating chapping in style conversion
  • Contour enhancement method for approximately simulating chapping in style conversion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0120] This embodiment provides a contour enhancement method that approximates the texture method in style transfer. The method adopts a contour enhancement model that approximates the texture method in style transfer, such as figure 1 As shown, the contour enhancement model that approximates the Cunning method in style migration is obtained based on the CycleGAN model construction; the method for constructing the contour enhancement model that approximates the Cunning method in style migration includes the following steps:

[0121] Step 1, use the keywords of "landscape painting" and "landscape photo" respectively, grab relevant pictures in the search engine through the crawler program and download them, and obtain a total of 2562 landscape photos (source domain) and 2363 landscape paintings (target domain).

[0122] Step 2, using manual screening method to eliminate irrelevant images. A total of 1,956 landscape photos and 1,884 landscape paintings have been preserved. Store...

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 contour enhancement method for approximately simulating a chapping method in style migration, which adopts a contour enhancement model for approximately simulating the chapping method in style migration, and the contour enhancement model for approximately simulating the chapping method in style migration is constructed and obtained based on a CE-CycleGAN model. According to the method, a CycleGAN-based unsupervised and contour-enhanced image style migration framework is developed, and style conversion from a landscape photo to a more landscape painting is realized according to the characteristics of the landscape painting, lines are concerned, constraint conditions are set and edge features are highlighted. A gradient conversion branch is added in a CycleGAN network, and a gradient guiding method is designed to effectively guide style conversion of gradient information from a picture to a drawing. According to visual features of human eyes, it is necessary to selectively enhance edge information in an image, that is to say, a strong edge with a large contrast is reserved instead of a weak edge with a small contrast.

Description

technical field [0001] The invention belongs to the technical field of computer vision and relates to style transfer, in particular to a contour enhancement method for approximately simulating the texture method in style transfer. Background technique [0002] Recently, the AI ​​(artificial intelligence) application that converts landscape photos into landscape paintings has become a popular point of interest for many art lovers and cultural relics protection. The role of artificial intelligence technology in extracting typical features reflecting the style of artworks and imitating paintings helps to train painting skills, innovate literary and artistic works, and inherit and protect traditional art. [0003] The transformation of landscape photos into landscape paintings is essentially a transfer of image style. GAN was proposed by Goodfellow et al. It is an effective method to achieve image style transfer, and has gradually become the mainstream method of image style tra...

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): G06F16/951G06K9/62G06V10/774G06N3/02G06T5/40G06T7/13
CPCG06F16/951G06T5/40G06T7/13G06N3/02G06F18/214
Inventor 彭先霖彭盛霖胡琦瑶彭进业王佳欣刘鑫煜范建平
Owner NORTHWEST UNIV
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