Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Generation method and device for dynamic picture

A dynamic picture and dynamic picture technology, applied in the network field, can solve the problems of single motion mode and low accuracy of dynamic pictures

Active Publication Date: 2018-10-12
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] It can be seen that the motion pattern obtained by the above method is relatively simple, resulting in low accuracy of generating dynamic pictures

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
  • Generation method and device for dynamic picture
  • Generation method and device for dynamic picture
  • Generation method and device for dynamic picture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] refer to figure 1 , which shows a flow chart of the steps of a method for generating a dynamic picture, including:

[0029] Step 101, generating a target vector, and using a prediction network to predict the target vector to obtain a foreground dynamic picture, a foreground mask dynamic picture and a background static picture.

[0030] Wherein, the target vector is a reference object for generating a dynamic picture. In practical applications, the target vector may be a randomly generated noise vector, or may be a vector obtained from a static picture, or may be a sum vector of a vector obtained from a static picture and a noise vector.

[0031] It can be understood that when the target vector is a noise vector, the generated dynamic picture has no reference, and the accuracy of the dynamic picture is low; when the target vector is a vector obtained from a static picture or a sum vector with the noise vector, the generated dynamic picture and The original static pictu...

Embodiment 2

[0046] The embodiment of the present application describes an optional dynamic picture generation method from the system architecture level.

[0047] refer to figure 2 , which shows a flow chart of specific steps of another method for generating a dynamic picture.

[0048] Step 201 , pre-training each network involved in the dynamic image generation step based on a preset dynamic image sample set.

[0049] Among them, the dynamic picture sample set includes a large number of dynamic pictures, the more the dynamic picture sample set, the longer the training time, the more accurate the training result; the smaller the dynamic picture sample set, the shorter the training time, the less accurate the training result.

[0050] It can be understood that the dynamic picture sample set can be obtained from the Internet or other methods. Embodiments of the present disclosure do not limit the manner of obtaining the dynamic picture sample set.

[0051] Specifically, first, a simulate...

Embodiment 3

[0097] refer to image 3 , which shows a structural diagram of a device for generating a dynamic picture, specifically as follows.

[0098] The foreground and background prediction module 301 is used to generate a target vector, and use a prediction network to predict the target vector to obtain a foreground dynamic picture, a foreground mask dynamic picture and a background static picture.

[0099] The splitting module 302 is configured to split the foreground dynamic picture and the foreground mask dynamic picture into at least one frame of foreground static picture and the corresponding foreground mask static picture.

[0100] The first dynamic prediction module 303 is used to input the first frame of the foreground static picture, the first frame of the foreground mask static picture and the background static picture into the first cell body of the long-term short-term memory network, and perform prediction to generate the first dynamic picture. One frame.

[0101] The s...

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 embodiment of the invention provides a generation method and device for a dynamic picture. The method comprises the steps that a target vector is generated, and the target vector is predicted by adopting a prediction network to obtain a foreground dynamic picture, a foreground masked dynamic picture and a background static picture; the foreground dynamic picture and the foreground masked dynamic picture are split into at least one foreground static picture frame and corresponding foreground masked static picture frames; the first foreground static picture frame, the first foreground maskedstatic picture frame and the background static picture are input to a first cell of a long short-term memory network, and a first picture frame of the dynamic picture is generated predictively; and the n foreground static picture frame, the corresponding foreground masked static picture frame and an n-1 picture frame of the dynamic picture are input to an n cell of the long short-termmemory network, and an n picture frame of the dynamic picture is generated predictively. Accordingly, the problem that the generation accuracy rate of the dynamic picture is low is solved, and the generation accuracy rate of the dynamic picture can be increased.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of network technology, and in particular to a method and device for generating a dynamic picture. Background technique [0002] On the shopping platform, product information can be displayed through static pictures and dynamic pictures. Among them, the display effect of dynamic pictures is better than that of static pictures. However, the production cost of dynamic pictures is relatively high. [0003] In the prior art, the invention patent CN104318596B proposes a method for generating dynamic pictures, including: firstly, by analyzing the dynamic pictures, to extract the entity element images in the dynamic pictures; The motion pattern of the entity is determined in the library; finally, a corresponding dynamic picture is generated based on the entity element image and its first motion pattern. [0004] It can be seen that the motion pattern obtained by the above method is relatively sim...

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 Applications(China)
IPC IPC(8): G06T13/80
CPCG06T13/80G06T2207/20084G06T2207/20081G06T2207/10016G06N3/088G06N3/044G06N3/045
Inventor 俞力金昕
Owner BEIJING SANKUAI ONLINE TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com