Back to results
US 2024/0198230 A1Published application
Reconstruction of occluded regions of a face using machine learning
AssigneeSony Interactive Entertainment Inc.
InventorsRATHISH KRISHNAN, Deepali Arya, Manoj Srivastava, Seema Kataria, Jason Wang
Life of this patent
Estimating the term…
Abstract
An image of a computer game player wearing a headset that occludes part of the face is input to a trained machine learning (ML) model, which outputs in response a full-face image that is not occluded for use in, e.g., social network settings related to the game.
Claims20
An apparatus comprising:
- at least one processor configured to:
- input to at least one machine learning (ML) model an image of a computer simulation player wearing a computer simulation headset that occludes at least a portion of the face of the player;
- receive from the ML model a full-face image of the player;
- and
- present the full-face image on a display.
2 more elements
The apparatus of claim 4, wherein the processor is configured to:
- overlay on the full-face image an image of a partially transparent simulation headset that does not occlude a face in the full-face image.
A device comprising:
- at least one computer storage that is not a transitory signal and that comprises instructions executable by at least one processor to:
- input to at least one machine learning (ML) model an image of a computer simulation player wearing a computer simulation headset that occludes at least a portion of the face of the player;
- and
- receive from the ML model a full-face image of the player for display thereof.
1 more element
A method comprising:
- receiving an image of a human face at least partially occluded by a computer simulation headset;
- inputting the image to at least one machine learning (ML) model;
- and
- receiving from the Ml model a full-face image of the player.
1 more element
Dependencies are inferred from the claim text.