Granted Patent B2

US 12,623,143 · App. 18/481,121 · Granted May 12, 2026

Inventors: Elizabeth Osborne (Oakland, CA); Angela Sun Wu (San Francisco, CA); Jin Zhang (Belmont, CA); Xi Zhou (Sunnyvale, CA); Hsin-Yi Chien (San Jose, CA); Olga Rudi (San Francisco, CA)

Assignee: Sony Interactive Entertainment Inc.

A63F13/355G06T3/40G06V10/764

Abstract

Claims (65)

1 . A method, comprising:

executing a video game to generate a video frame for presentation on a first device of a first platform, wherein the video frame is generated for a game play of the video game by a user;

determining a target device, wherein the target device is of a second platform;

mapping the video frame from the first device to the target device, wherein the video frame that is mapped is presented on the target device;

determining an area of focus in a scene of the game play presented in the video frame based on a game context of the scene in the game play;

classifying an asset in the area of focus using a computer vision model implementing artificial intelligence;

determining that the asset is important in the game play of the video game using the computer vision model;

dumb scaling the video frame to a smaller size for presentation on the target device;

determining that the asset in the dumb scaled video frame that is mapped to the target device does not meet a threshold of visibility; and

modifying the dumb scaled video frame that is mapped so that the asset meets the threshold of visibility.

2 . The method of claim 1 , further comprising:

sending the video frame that is mapped and modified to the target device.

3 . The method of claim 1 , wherein the modifying the video frame that is mapped includes:

transforming the asset through rescaling; and

overlaying the asset that is rescaled within the video frame that is mapped.

4 . The method of claim 1 , wherein the modifying the video frame that is mapped includes:

changing a field of view (FOV) of the scene to the area of focus; and

limiting the video frame that is modified to the FOV that is changed.

5 . The method of claim 1 , wherein the determining the area of focus includes:

determining a focus of interaction by the user in the scene of the game play.

6 . The method of claim 1 , further comprising:

training the computer vision model using a list of assets for the video game.

7 . A non-transitory computer-readable medium storing a computer program for execution by a processor to perform a method, the non-transitory computer-readable medium comprising:

program instructions for executing a video game to generate a video frame for presentation on a first device of a first platform, wherein the video frame is generated for a game play of the video game by a user;

program instructions for determining a target device, wherein the target device is of a second platform;

program instructions for mapping the video frame from the first device to the target device, wherein the video frame that is mapped is presented on the target device;

program instructions for determining an area of focus in a scene of the game play presented in the video frame based on a game context of the scene in the game play;

program instructions for classifying an asset in the area of focus using a computer vision model implementing artificial intelligence;

program instructions for determining that the asset is important in the game play of the video game using the computer vision model;

program instructions for dumb scaling the video frame for presentation on the target device;

program instructions for determining that the asset in the dumb scaled video frame that is mapped to the target device does not meet a threshold of visibility; and

program instructions for modifying the dumb scaled video frame that is mapped so that the asset meets the threshold of visibility.

8 . The non-transitory computer-readable medium of claim 7 , further comprising:

program instructions for sending the video frame that is mapped and modified to the target device.

9 . The non-transitory computer-readable medium of claim 7 , wherein the program instructions for modifying the video frame that is mapped includes:

program instructions for transforming the asset through rescaling; and

program instructions for overlaying the asset that is rescaled within the video frame that is mapped.

10 . The non-transitory computer-readable medium of claim 7 , wherein the program instructions for modifying the video frame that is mapped includes:

program instructions for changing a field of view (FOV) of the scene to the area of focus; and

program instructions for limiting the video frame that is modified to the FOV that is changed.

11 . The non-transitory computer-readable medium of claim 7 , wherein the program instructions for determining the area of focus includes:

program instructions for determining a focus of interaction by the user in the scene of the game play.

12 . The non-transitory computer-readable medium of claim 7 , further comprising:

program instructions for training the computer vision model using a list of assets for the video game.

13 . A computer system comprising:

a processor;

memory coupled to the processor and having stored therein instructions that, if executed by the computer system, cause the computer system to execute a method for implementing a graphics pipeline, comprising:

executing a video game to generate a video frame for presentation on a first device of a first platform, wherein the video frame is generated for a game play of the video game by a user;

determining a target device, wherein the target device is of a second platform;

mapping the video frame from the first device to the target device, wherein the video frame that is mapped is presented on the target device;

determining an area of focus in a scene of the game play presented in the video frame based on a game context of the scene in the game play;

dumb scaling the video frame for presentation on the target device;

determining an asset in the area of focus is important in the game play of the video game using a computer vision model implementing artificial intelligence;

classifying the asset using the computer vision model;

determining that the asset in the dumb scaled video frame that is mapped to the target device does not meet a threshold of visibility; and

modifying the dumb scaled video frame that is mapped so that the asset meets the threshold of visibility.

14 . The computer system of claim 13 , the method further comprising:

sending the video frame that is mapped and modified to the target device.

15 . The computer system of claim 13 , wherein in the method the modifying the video frame that is mapped includes:

changing a field of view (FOV) of the scene to the area of focus; and

limiting the video frame that is modified to the FOV that is changed.

16 . The computer system of claim 13 , wherein in the method the determining the area of focus includes:

determining a focus of interaction by the user in the scene of the game play.

17 . The computer system of claim 13 , the method further comprising:

training the computer vision model using a list of assets for the video game.

Assignments (1)

Continuity (1)

References Cited (9)