Virtual image video generation method and device, computer equipment and storage medium

A virtual image and video technology, applied in the field of artificial intelligence image processing, can solve problems such as difficulty in obtaining a large number of real face pictures and unsatisfactory virtual video.

Pending Publication Date: 2020-09-22
PINGAN PUHUI ENTERPRISE MANAGEMENT CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, at present, the industry generally replaces the video with real face pictures to obtain virtual videos. In practical applications, it is often difficult to obtain a sufficient number of real face pictures with rich expressions, and directly perform face replacement based on real face pictures. The generated virtual video is not ideal

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
  • Virtual image video generation method and device, computer equipment and storage medium
  • Virtual image video generation method and device, computer equipment and storage medium
  • Virtual image video generation method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] figure 1 It is a flow chart of the method for generating an avatar video provided by Embodiment 1 of the present invention. The virtual image video generation method is applied to computer equipment. The avatar video generating method uses a virtual human face picture to replace the face of the target video to obtain the avatar video.

[0063] like figure 1 As shown, the virtual image video generation method includes:

[0064] 101. Determine a first character and a second character used to generate a virtual human face picture, and determine weights of the first character and the second character.

[0065] In one embodiment, the determining the first person and the second person used to generate the virtual human face picture, and determining the weights of the first person and the second person include:

[0066] Generate character and weight setting interface;

[0067] receiving the two characters and the weights of the two characters set by the user from the char...

Embodiment 2

[0138] figure 2 It is a structural diagram of the avatar video generation device provided by Embodiment 2 of the present invention. The virtual image video generation device 20 is applied to computer equipment. The avatar video generating device 20 replaces the face of the target video with a virtual human face picture to obtain the avatar video.

[0139] like figure 2 As shown, the avatar video generation device 20 may include a first determination module 201 , an acquisition module 202 , a generation module 203 , an extraction module 204 , a second determination module 205 , a replacement module 206 , and a synthesis module 207 .

[0140] The first determining module 201 is configured to determine a first character and a second character for generating a virtual human face picture, and determine weights of the first character and the second character.

[0141] In one embodiment, the determining the first person and the second person used to generate the virtual human fa...

Embodiment 3

[0214] This embodiment provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above embodiment of the method for generating an avatar video are implemented, for example figure 1 101-107 shown.

[0215] Alternatively, when the computer program is executed by the processor, the functions of the modules in the above-mentioned device embodiments are realized, for example figure 2 Modules 201-207 in.

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 the technical field of artificial intelligence, and provides a virtual image video generation method. The virtual image video generation method comprises the following steps:determining a first figure and a second figure for generating a virtual face picture and weights thereof; obtaining a preset number of human face picture pairs of the first person and the second person; according to the weights of the first figure and the second figure, generating a candidate virtual face picture for each face picture pair by utilizing a picture generation model; extracting each frame of target picture in the target video; determining a target virtual face picture similar to the expression of the target picture from the candidate virtual face pictures; performing face replacement on the target picture according to the target virtual face picture to obtain a face replacement picture; and synthesizing the face replacement picture into the target video to obtain a virtual image video. According to the invention, a high-quality virtual image video can be obtained. The invention also relates to a blockchain technology, and the face picture pair is stored in the blockchain.

Description

technical field [0001] The invention relates to the technical field of image processing of artificial intelligence, in particular to a virtual image video generation method, device, computer equipment and storage medium. Background technique [0002] For systems that require customer service, human agents are often required to provide services through real video. Traditional artificial seats have low work efficiency and are difficult to improve, and the operating costs are relatively high. Using virtual video instead of real video of artificial seats can solve these problems, improve service quality, and improve customer satisfaction. However, at present, the industry generally replaces the video with real face pictures to obtain virtual videos. In practical applications, it is often difficult to obtain a sufficient number of real face pictures with rich expressions, and directly perform face replacement based on real face pictures. The resulting virtual video is not ideal...

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): G06T3/00G06T7/11G06T5/00G06K9/00G06K9/62G06Q30/00
CPCG06T7/11G06Q30/01G06T2207/10016G06T2207/20182G06V40/171G06V40/174G06V40/161G06F18/22G06T3/04G06T5/70Y02D10/00
Inventor 南海顺
Owner PINGAN PUHUI ENTERPRISE MANAGEMENT CO LTD
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