System for automatically generating animation scene

An automatic generation and scene technology, applied in the direction of animation production, natural language data processing, image data processing, etc., can solve the problem that the scene cannot input dynamic changes, etc., and achieve the effect of improving the effect

Pending Publication Date: 2022-02-08
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The existing animation scene automatic generation technology generally needs to annotate animation elements for each sample in the animation scene training set, so the constructed scene cannot dynamically change according to the specific input

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
  • System for automatically generating animation scene
  • System for automatically generating animation scene
  • System for automatically generating animation scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] Such as figure 1 As shown, the present embodiment relates to a method for automatically generating an animation scene, comprising the following steps:

[0019] Step 1. Data set preprocessing: generate a data set and define rules in different aspects according to data characteristics, including:

[0020] 1.1) Obtain domestic and foreign fairy tale data sets, and obtain data in plain text form: this embodiment uses "Andersen's Fairy Tales", "Grimm's Fairy Tales" and "Chinese Classic Fairy Tales"

[0021] 1.2) Statistical natural environment and man-made environment, through the clustering algorithm of HowNet semantic similarity, classify the scene: Semantic similarity Sim(w 1 ,w 2 ) = Max i＝1，...，n，j＝1，...，m Sim(s 1 ,s 2 ), where: w 1 and w 2 represent two words respectively, s 1 and s 2 Indicates two different sememes; similarity d is s 1 and s 2 In the path distance in the hierarchy tree, a is an adjustable parameter.

[0022] The scene in this embodiment ...

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

A system for automatically generating an animation scene comprises a data preprocessing unit, a knowledge graph construction unit, a text analysis unit and a scene generation unit, performs statistical classification on a natural environment and an artificial environment, selects a scene most conforming to a plot and defines constraint rules at different times according to the natural environment and the artificial environment, the change of the same scene at different time is displayed in this way; the orientation relation of different entities is defined, the scene is refined in sequence, the whole background is generated by splicing all the entities, the problem that a material library does not completely meet plot requirements is solved, and the scheme of automatically generating the scene under the condition that materials are missing and incomplete can be achieved.

Description

technical field [0001] The invention relates to a technology in the field of computer image processing, in particular to an automatic generation system of animation scenes. Background technique [0002] The existing animation scene automatic generation technology generally needs to annotate animation elements for each sample in the animation scene training set, so the constructed scene cannot dynamically change according to the specific input. Contents of the invention [0003] Aiming at the above-mentioned deficiencies in the prior art, the present invention proposes an automatic animation scene generation system, which statistically classifies the natural environment and the man-made environment, selects the scene that best fits the plot and defines the constraint rules at different times, and then presents The change of the same scene at different times; define the orientation relationship of different entities, refine the scene accordingly, and generate the entire back...

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): G06T13/00G06F16/36G06F16/35G06F40/30G06F40/211
CPCG06T13/00G06F16/367G06F16/35G06F40/30G06F40/211
Inventor 谭淳李国强
Owner SHANGHAI JIAO TONG 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