Intelligent face editing method and device, storage medium and equipment

A technology of smart people and editing, applied in the field of smart face editing, which can solve problems such as the inability to generate a human face, the inability to edit the overall appearance of a human face, etc.

Active Publication Date: 2021-06-18
中科计算技术创新研究院
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, existing techniques cannot edit the overall appearance of a face, nor ...

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
  • Intelligent face editing method and device, storage medium and equipment
  • Intelligent face editing method and device, storage medium and equipment
  • Intelligent face editing method and device, storage medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] like figure 1 As shown, this embodiment uses the image decoupling technology and adopts a local-to-global method to propose an intelligent face editing method.

[0057] In this example, the face is divided into five parts: left eye, right eye, nose, mouth, and background. After the image is divided into blocks, a local decoupling module is designed to extract and generate decoupling features for each part of the image. ; After obtaining the generation results of each part, splicing and fusing the block results through the global fusion module to obtain a face image result with global consistency.

[0058] The network structure of this embodiment includes 5 local decoupling modules for decoupling geometry and appearance information, and 1 global fusion module to realize the fusion of local features and generate high-quality, globally consistent results. In the process of network training, the strategy of exchange is used, and the feature constraints of cycle consistency...

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 an intelligent face editing method and device, a storage medium and equipment. The invention is suitable for the fields of computer vision and computer graphics. The invention provides an intelligent face editing method and device, a storage medium and equipment. According to the technical scheme, the intelligent face editing method is characterized in that a face geometric feature image and a face appearance feature image are input into a corresponding trained local decoupling module according to face parts, and geometric features and appearance features corresponding to all the parts of the face are extracted; the local decoupling module generates a local image and a local intermediate feature map corresponding to each part of the human face based on the geometric features and the appearance features; and the local intermediate feature maps corresponding to the parts of the human face are fused through a trained global fusion module to generate a final human face image with the geometric features and the appearance features.

Description

technical field [0001] The invention relates to an intelligent face editing method, device, storage medium and equipment. Applicable to the fields of computer vision and computer graphics. Background technique [0002] Face synthesis technology is one of the important topics in the field of digital image processing, and there are many related technologies around high-quality face synthesis. The face synthesis technology based on deep learning mainly has the following two types: through Gaussian sampling, use the generative confrontation network (GAN) to synthesize new faces; use the conditional generative confrontation network to input semantic markup maps, sketches, attribute labels, etc. information to synthesize the corresponding face. Although there are many technologies for synthesizing real faces through sketches, most of them cannot control the appearance of the generated faces, or the effect of face synthesis is poor. [0003] For face editing, some existing techn...

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): G06T11/00G06T5/50
CPCG06T5/50G06T11/00G06T2207/20081G06T2207/20221G06T2207/30201
Inventor 高林陈姝宇刘锋林
Owner 中科计算技术创新研究院
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