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

A real-time calculation method of digital human cloth based on deep learning

A deep learning and digital human technology, applied in neural learning methods, computing, image data processing, etc., can solve the problems of manual manual finishing, low efficiency of fabric production, interspersed fabric and character models, etc., to avoid interspersed and improve production. The effect of efficiency

Active Publication Date: 2021-04-16
江苏原力数字科技股份有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Due to the nature of the calculation process of modeling simulation, the specific size and shape of the cloth must be changed according to the change of the character model, otherwise it will lead to the phenomenon that the cloth and the character model are interspersed, and manual refinement is required
[0004] After the cloth animation is solved, if the character skeleton animation is modified in the later stage, the corresponding cloth animation needs to be recalculated to generate a new cache, and the cloth production efficiency is low.

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
  • A real-time calculation method of digital human cloth based on deep learning
  • A real-time calculation method of digital human cloth based on deep learning
  • A real-time calculation method of digital human cloth based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] A real-time calculation method for digital human cloth based on deep learning, which uses neural networks to replace complicated modeling and simulation, greatly reducing computing costs. Since the movements required by the digital human are not complicated, the skin mesh and the cloth mesh of the digital human can be integrated to avoid interleaving problems that may be caused by the solution, and no manual refinement is required;

[0032] The digital human skin mesh and the cloth mesh are integrated so that the skeleton of the digital human can drive the three-dimensional coordinates of the mesh vertices of the cloth. The mapping relationship from the bone to the mesh vertices of the cloth can be regarded as a complex nonlinear function, and a neural network is used to learn this mapping relationship. The skeleton information (rotation and translation) of the digital human is used as the input of the neural network, and through training, the three-dimensional coordina...

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 present invention provides a real-time calculation method for digital human cloth based on deep learning, which includes the following steps: S1: training neural network, training autoencoder and fully connected network to map skeleton information to the coding of cloth grid vertices; S2: in After training the above two neural networks, given a set of input skeleton information, first pass through the fully connected network to obtain the code of the vertices of the cloth mesh, and then pass through the decoding link in the autoencoder to obtain the vertices of the output cloth mesh, the output It is the calculation result of the cloth. The present invention calculates the grid vertex information of the cloth in real time, effectively avoids the problem of character models interspersed with the cloth model, and further improves the cloth production efficiency.

Description

technical field [0001] The invention belongs to the technical field of animation production, and in particular relates to a real-time calculation method for digital human cloth based on deep learning. Background technique [0002] In the current film and television animation production process, the animation data of clothing cloth is calculated by establishing a mathematical physical model to simulate the movement of the cloth in a real scene to calculate the final effect, that is, the three-dimensional coordinate value of the vertices of the cloth mesh in each frame. Modeling and simulation means that calculating the three-dimensional coordinates of the vertices of each frame consumes a lot of resources. Therefore, the current digital human cloth generally adopts the offline calculation method, that is, the cloth of each frame is calculated in advance according to the skeleton animation of the character. Grid vertex information, written into the cache, and called out when n...

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 Patents(China)
IPC IPC(8): G06T13/40G06N3/04G06N3/08
CPCG06T13/40G06N3/08G06N3/045
Inventor 赵锐侯志迎
Owner 江苏原力数字科技股份有限公司
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