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

Human body animation synthesis method based on human body soft tissue grid model

A technology of mesh model and human animation

Pending Publication Date: 2020-11-20
GUANGDONG UNIV OF TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a soft tissue motion human animation synthesis method based on the redirection of the human body mesh model to solve the problem that it is difficult to capture accurate soft tissue motion in the prior art and requires complicated post-processing work

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
  • Human body animation synthesis method based on human body soft tissue grid model
  • Human body animation synthesis method based on human body soft tissue grid model
  • Human body animation synthesis method based on human body soft tissue grid model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention proposes an end-to-end synthesis method of human body animation including soft tissue movement, which eliminates the current skeletal animation scheme of animation redirection, and uses human soft tissue mesh model to redirect to the target animation model instead. The present invention proposes a deep learning method to learn the skeleton key point coordinates of the target character's three-dimensional posture θ, and at the same time to learn the UV texture of the surface shape β of the human soft tissue (the pixels of the video frame are corresponding to the continuous points of the soft tissue surface of the human soft tissue grid model) coordinate). According to the three-dimensional pose θ of the character and the surface shape of the human body β, the human soft tissue mesh model can be reconstructed, and the human body animation can be generated by redirecting the human soft tissue mesh model.

[0037] Among them, the present invention uses...

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 human body animation synthesis method based on a human body soft tissue grid model, and the method comprises the steps: firstly extracting the features of different dimensions of an image through a feature pyramid network, and then inputting the features of different dimensions into subsequent tasks such as human body part segmentation, soft tissue texture and posture estimation through a region-feature alignment technology.; and according to the three-dimensional posture and the soft tissue texture, mapping the figure in the original image to a three-dimensional human body soft tissue grid model to achieve reconstruction of the human body soft tissue grid model, and then achieved human body animation synthesis through redirection of the human body soft tissue grid model. By using the method of combining the human body soft tissue mesh model and the deep learning, the human body soft tissue motion can be accurately captured, so that the synthesized human bodyanimation details are richer in expression.

Description

technical field [0001] The invention relates to the field of algorithms for film and television production and virtual reality motion capture, and in particular to a method for synthesizing soft tissue motion human animation based on human body grid model redirection. Background technique [0002] The current motion capture system represented by the optical motion capture system relies on setting physical tracking points, relying on expensive and bloated external devices such as lasers and photosensitive sensors to determine the position of moving objects, and requires complicated post-processing work; and because setting physical tracking With a limited number of points, it is almost impossible for them to capture precise soft tissue motion. [0003] The current animation retargeting synthesis technology is limited to skeletal animation schemes. The skeleton is used to describe the action information, and the skin is used to represent the relationship between the human mesh...

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): G06T13/60
CPCG06T13/60
Inventor 王卓薇林伟达
Owner GUANGDONG UNIV OF TECH
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