Patent · US Active

Particle-based inverse kinematic rendering system

US10535174B1 · kind B1 · utility

82Cited by
33References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 14, 2017
Grant dateJan 14, 2020
Priority date
Expiry dateDec 18, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2213/12
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The present disclosure provides embodiments of a particle-based inverse kinematic analysis system. The inverse kinematic system can utilize a neural network, also referred to as a deep neural network, which utilizes machine learning processes in order to create poses that are more life-like and realistic. The system can generate prediction models using motion capture data. The motion capture data can be aggregated and analyzed in order to train the neural network. The neural network can determine rules and constraints that govern how joints and connectors of a character model move in order to create realistic motion of the character model within the game application.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.