US 12,420,200 B2
Reconstruction of occluded regions of a face using machine learning
Rathish Krishnan, San Mateo, CA (US); Deepali Arya, San Mateo, CA (US); Manoj Srivastava, San Mateo, CA (US); Seema Kataria, San Mateo, CA (US); and Jason Wang, San Mateo, CA (US)
Assigned to Sony Interactive Entertainment Inc., Tokyo (JP)
Filed by Sony Interactive Entertainment Inc., Tokyo (JP)
Filed on Dec. 14, 2022, as Appl. No. 18/066,255.
Prior Publication US 2024/0198230 A1, Jun. 20, 2024
Int. Cl. A63F 13/655 (2014.01); A63F 13/213 (2014.01)
CPC A63F 13/655 (2014.09) [A63F 13/213 (2014.09)] 20 Claims
OG exemplary drawing
 
1. An apparatus comprising:
at least one processor configured to perform operations comprising:
inputting, 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;
receiving, as output from the ML model, a full-face image of the player;
inputting, to a post-processing ML model, an image of a mouth of the player;
receiving, as output from the post-processing ML model, information indicating a facial expression of the player;
generating a modified full-face image of the player using the information indicating the facial expression of the player; and
presenting the modified full-face image on a display.