Virtual image generation model training method and virtual image generation method

A technology for generating models and avatars, applied in character and pattern recognition, instrumentation, computing, etc., and can solve problems such as insufficient flexibility, high cost, and difficult mesh mapping relationships

Active Publication Date: 2022-03-04
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF9 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, the generation of avatars from text can only be achieved through matching, that is, through manual annotation, labeling attribute tags for avatars, and manually setting mapping relationships. However, this method is costly and inflexible. For complex and large-scale semantic structures, manual annotation is required. It is difficult to build a deeper mesh mapping relationship

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 generation model training method and virtual image generation method
  • Virtual image generation model training method and virtual image generation method
  • Virtual image generation model training method and virtual image generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0026] figure 1 An exemplary system architecture 100 of an embodiment of the avatar generation model training method or avatar generation method or avatar generation model training device or avatar generation device that can be applied is shown.

[0027] like figure 1 As shown, the system architecture 100 may include terminal devices 101 , 102 , 103 , a network 104 an...

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 training method of a virtual image generation model, a virtual image generation method and device, equipment, a storage medium and a computer program product, relates to the technical field of artificial intelligence, in particular to the technical field of virtual / augmented reality, computer vision and deep learning, and can be applied to scenes such as virtual image generation. According to the specific implementation scheme, a standard image sample set and a random vector sample set serve as first sample data, a first initial model is trained, and an image generation model is obtained; taking the test implicit vector sample set and the test image sample set as second sample data, and training the second initial model to obtain an image coding model; taking the standard image sample set and the description text sample set as third sample data, and training the third initial model to obtain an image editing model; and based on the above model, training the fourth initial model by using the third sample data to obtain a virtual image generation model. The efficiency of generating the virtual image is improved, and the user experience is improved.

Description

technical field [0001] The present disclosure relates to the field of artificial intelligence technology, specifically the field of virtual / augmented reality, computer vision and deep learning technology, which can be applied to scenes such as avatar generation, and in particular to a training method for a virtual image generation model, a virtual image generation method, and a device , equipment, storage media and computer program products. Background technique [0002] At present, the generation of avatars from text can only be achieved through matching, that is, through manual annotation, labeling attribute tags for avatars, and manually setting mapping relationships. However, this method is costly and inflexible. For complex and large-scale semantic structures, manual annotation is required. It is difficult to construct a deeper mesh mapping relationship. Contents of the invention [0003] The present disclosure provides a training method for a virtual image generatio...

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): G06T19/00G06K9/62G06V10/774
CPCG06T19/006G06F18/214G06V10/774G06V10/776G06V10/82G06T19/00G06T2207/20081G06F18/00G06T11/60
Inventor 彭昊天赵晨
Owner BEIJING BAIDU NETCOM SCI & TECH 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