Back to results
US 11,847,743 B2Granted
Voice driven modification of physical properties and physics parameterization in a closed simulation loop for creating static assets in computer simulations
AssigneeSony Interactive Entertainment Inc.
InventorsSudha Krishnamurthy, Michael Taylor
Life of this patent
Estimating the term…
Abstract
A computer simulation object such as a chair is described by voice or photo input to render a 2D image. Machine learning may be used to convert voice input to the 2D image. The 2D image is converted to a 3D object and the 3D object or portions thereof are used in the computer simulation, such as a computer game, as the object such as a chair. A physics engine can be used to modify the 3D objects.
Claims12
A method comprising:
- using at least one neural network, generating a three-dimensional (3D) object of a computer simulation asset;
- processing information associated with the asset using at least one physics engine to render an output;
- feeding the output back to the neural network;
- receiving from the neural network a modified asset in response to feeding back the output of the physics engine to the neural network;
- rendering the output of the physics engine at least in part by modifying the information associated with the asset to maintain zero torque on plural portions of the asset;
- and
- using the asset in at least one computer game.
4 more elements
An apparatus comprising:
- at least one processor configured to:
- using at least one neural network, generate a three-dimensional (3D) object of a computer simulation asset;
- process information associated with the asset using at least one physics engine to render an output;
- feed the output back to the at least one neural network;
- receive from the at least one neural network a modified asset in response to feeding back the output of the physics engine to the at least one neural network;
- render the output of the physics engine at least in part by modifying the information associated with the asset to maintain zero torque on plural portions of the asset;
- and
- use the asset in at least one computer game.
5 more elements
An apparatus comprising:
- at least one computer medium that is not a transitory signal and that comprises instruction executable by at least one processor to:
- using at least one neural network, generate a three-dimensional (3D) object of a computer simulation asset;
- process information associated with the asset using at least one physics engine to render an output;
- feed the output back to the at least one neural network;
- receive from the at least one neural network a modified asset in response to feeding back the output of the physics engine to the at least one neural network;
- render the output of the physics engine at least in part by modifying the information associated with the asset to maintain zero torque on plural portions of the asset;
- and
- use the asset in at least one computer game.
5 more elements
Dependencies are inferred from the claim text.