A Face Caricature Generation Method Based on Recurrent Space Transformation Network

A technology of space conversion and space circulation, which is applied in the generation of 2D images, neural learning methods, biological neural network models, etc., can solve the problems that are not suitable for the generation of human face caricatures, so as to improve the quality and aesthetics of pictures, and achieve both Fun and Artistic Effects

Active Publication Date: 2021-03-05
ZHEJIANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

So they are not suitable for solving the problem of face caricature generation

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 Face Caricature Generation Method Based on Recurrent Space Transformation Network
  • A Face Caricature Generation Method Based on Recurrent Space Transformation Network
  • A Face Caricature Generation Method Based on Recurrent Space Transformation Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be noted that the following embodiments are intended to facilitate the understanding of the present invention, but do not limit it in any way.

[0038] Such as figure 1 As shown, the present invention divides the face caricature generation into a space conversion model and a texture conversion model, and trains and tests these two models respectively.

[0039] The specific framework of the image conversion module is as follows: figure 2 shown. Using the heat map of key points of the face as input, after several layers of convolutional neural networks, the parameters for spatial transformation are directly predicted. Then apply this space transformation to the heat map, and you can get the heat map of the key points of the face that has undergone geometric deformation.

[0040] The specific framework of the recurrent space transformatio...

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 face caricature generation method based on a cyclic space transformation network, comprising: (1) selecting a training data set, analyzing photos and face caricature parts in the data set, and obtaining key point information of the face; (2) According to the key point information of the face, establish a space conversion model based on a recurrent space conversion network; (3) train and test the space conversion model; (4) establish a texture conversion model between photos and face caricatures, and conduct training Optimization; (5) Input the photos to be converted into the trained space transformation model, and send the space transformation result into the texture transformation model, and finally obtain high-quality face cartoons. Utilizing the invention, the generated human face caricature can not only have an exaggerated geometric structure, but also have an artistic style in texture and color, which greatly improves the aesthetics and interest.

Description

technical field [0001] The invention belongs to the field of image generation and conversion in computer vision, and in particular relates to a method for generating human face cartoons based on a cyclic space conversion network. Background technique [0002] Face caricature refers to the drawing of normal human faces in an exaggerated and artistic way to achieve satirical or humorous visual effects. They are widely used to describe celebrities or politicians for entertainment purposes. [0003] Ergun Akleman et al. from Texas A&M University proposed an interactive program for generating caricatures in the article "Making Extreme Caricatures with a New Interactive 2D Deformation Technique with Simplicial Complexes" in the Journal of Visualization in 2000. Their program defines the meaning of key points of many facial features in advance, and then asks the user to specify the position of key points in photos and caricatures. Based on these keypoint correspondences, their pr...

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 Patents(China)
IPC IPC(8): G06T11/00G06K9/00G06N3/04G06N3/08
CPCG06T11/001G06N3/08G06V40/165G06V40/168G06N3/045
Inventor 储文青蔡登
Owner ZHEJIANG 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