End-to-end rapid reconstruction method for gas scene under limited view

A gas and scene technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as complex, time-consuming optimization and discrete operations, and achieve the effects of ensuring realism, avoiding optimized calculations, and efficient calculations

Active Publication Date: 2021-02-19
EAST CHINA NORMAL UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, complex and time-consuming optimization and discretization operations are still required due to numerical calculations

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
  • End-to-end rapid reconstruction method for gas scene under limited view
  • End-to-end rapid reconstruction method for gas scene under limited view
  • End-to-end rapid reconstruction method for gas scene under limited view

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] See attached figure 1 , the present invention performs fluid animation parameter estimation and detail enhancement according to the following steps:

[0053] (1) Preliminary estimation of density field based on generative model

[0054] a. Set a random initial smoke source and velocity field, generate and collect the density field of the simulated fluid through the Euler method, and the corresponding front view and side view as training samples and generate a training data set.

[0055] b. Construct and train the conditional generation network; use the trained network to generate the density field by inputting the front view and side view sequences of the fluid animation, and obtain the preliminary density field reconstruction result.

[0056] (2) Velocity field reconstruction based on convolutional neural network

[0057] a. Collect the gas scene data generated by the Euler method as a training sample and generate a training data set, mainly including the velocity fi...

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 gas scene end-to-end rapid reconstruction method under a limited view, which is characterized in that the gas scene end-to-end rapid reconstruction method specifically comprises the following steps: 1) generating a preliminary estimated density field; 2) reconstructing a velocity field; 3) optimizing a density field; and 4) according to the reconstructed physical field ofthe gas scene, generating a more attractive result and a richer visual detail effect. Compared with the prior art, the method has the advantages that the gas scene is quickly and effectively reconstructed by inputting the front view and side view sequences, and detail enhancement method or artistry control is performed, so that the reconstruction performance of the smoke scene is greatly improved, and the effectiveness and robustness of the reconstruction result are ensured.

Description

technical field [0001] The invention relates to the technical field of computer graphics, in particular to an end-to-end rapid reconstruction method of a gas scene under a limited view by borrowing a large amount of training data and an artificial neural network. Background technique [0002] With the increasing maturity of rigid body animation simulation technology, the capture of dynamic physical phenomena has been an active research topic in the field of graphics and vision in recent decades. Due to hardware and setup constraints and reliance on complex numerical optimization and discretization operations, the capture of dynamic physical phenomena is ubiquitous and the reconstruction process often requires substantial equipment and computational costs. However, in many applications, the speed and simplicity of data capture are what people need. Real-time capture of dynamic physical phenomena can greatly promote the development of fluid simulation and play an irreplaceable...

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): G06F30/27G06K9/62G06N3/04G06N3/08G06F113/08
CPCG06F30/27G06N3/084G06F2113/08G06N3/045G06F18/214
Inventor 邱晟李晨王长波秦洪
Owner EAST CHINA NORMAL 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