Portrait three-dimensional model and simulation portrait animation generation method and device and medium

A technology of 3D models and portraits, which is applied in the field of image processing, can solve problems such as insufficient visual effects and achieve the effect of improving interactive fun

Pending Publication Date: 2020-09-22
GUANGDONG KANGYUN TECH LTD
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the prior art, the 3D model of the portrait and the animation of the simulated portrait are usually pre-made or recorded, and played out during use, but this cannot provide interactive effects to the audience, resulting in the displayed visual effect not being vivid enough

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
  • Portrait three-dimensional model and simulation portrait animation generation method and device and medium
  • Portrait three-dimensional model and simulation portrait animation generation method and device and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] In this embodiment, the method for generating a three-dimensional portrait model will use an artificial intelligence model. In this embodiment, the artificial intelligence model can be a long-short-term memory artificial neural network, an integrated moving average autoregressive model, a support vector machine, a logistic regression model and an Xgboost model, etc., and their common feature is that they are more suitable for processing and forming time series data, other artificial intelligence models based on neural networks can also be used.

[0042] Before performing the generation method of the portrait three-dimensional model, the artificial intelligence model is trained, and the training process includes the following steps:

[0043] P1. Obtain multiple two-dimensional portrait samples and their labels;

[0044] P2. Determine a plurality of first time series according to each of the two-dimensional portrait samples and their acquisition time;

[0045] P3. Deter...

Embodiment 2

[0070] The method for generating a simulated portrait animation described in this embodiment is executed based on the method for generating a three-dimensional portrait model in Embodiment 1. refer to figure 2 , the generation method of simulated portrait animation comprises the following steps:

[0071] Q1. Detect interactive operations; in this embodiment, one or more executors can perform interactive operations through interactive operations such as keyboards and touch screens; one or more executors can also perform interactive operations through actions such as facial expressions or gestures. screen, from which interactive operations are identified;

[0072] Q2. Execute the generation method of the portrait three-dimensional model in embodiment 1, that is, steps S1-S4, etc., to respond to the interactive operation;

[0073] Q3. Executing steps S1-S4 will obtain a 3D model of the portrait. According to the generated 3D model of the portrait, further processing such as co...

Embodiment 3

[0080] In this embodiment, a computer device includes a memory and a processor, the memory is used to store at least one program, and the processor is used to load the at least one program to execute the generation of the three-dimensional portrait model described in Embodiment 1 The method and the method for generating a simulated portrait animation described in Embodiment 2 achieve the same technical effects as those described in Embodiment 1 and Embodiment 2.

[0081] In this embodiment, a storage medium stores processor-executable instructions therein, and when the processor-executable instructions are executed by a processor, they are used to execute the method for generating a three-dimensional portrait model described in Embodiment 1 and The method for generating a simulated portrait animation described in Embodiment 2 achieves the same technical effect as that described in Embodiment 1 and Embodiment 2.

[0082] It should be noted that, unless otherwise specified, when...

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 discloses a portrait three-dimensional model generation method, a simulation portrait animation generation method, a computer device and a storage medium. The portrait three-dimensionalmodel generation method comprises the steps of acquiring a plurality of portrait two-dimensional pictures, determining a time sequence, inputting the time sequence into a trained artificial intelligence model, acquiring a portrait three-dimensional model output by the artificial intelligence model and the like. The trained artificial intelligence model can process the portrait two-dimensional picture, the corresponding expression base and the portrait three-dimensional model are obtained; the portrait three-dimensional model and the portrait two-dimensional picture have corresponding expressions, the corresponding relation can be changed by adjusting the training process of the artificial intelligence model, the finally obtained portrait three-dimensional model can present a vivid effect,and the interaction fun is improved. The simulation portrait animation generation method is executed on the basis of the method for generating the portrait three-dimensional model, and the same effectcan also be generated. The invention is widely applied to the technical field of image processing.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for generating a three-dimensional model of a portrait, a method for generating a simulated portrait animation, a computer device and a storage medium. Background technique [0002] In the fields of video games, self-service customer service, and video production, it is necessary to generate 3D models of portraits or simulated portrait animations. The three-dimensional portrait model refers to a three-dimensional image model used to display a portrait image, and the simulated portrait animation refers to an animation containing a simulated portrait image. In the prior art, the 3D model of the portrait and the animation of the simulated portrait are usually produced or recorded in advance, and played out during use, but this cannot provide interactive effects to the audience, resulting in the displayed visual effect not being vivid enough. Contents of the inven...

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): G06T13/40G06T17/00G06K9/62G06T15/00
CPCG06T13/40G06T17/00G06T15/005G06F18/214
Inventor 李新福
Owner GUANGDONG KANGYUN TECH 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