Hyper-personalized game items

Patent metadata

Field	Value
Publication number	US-12427424-B2
Application number	US-202217938322-A
Country	US
Kind code	B2
Filing date	Oct 5, 2022
Priority date	Oct 5, 2022
Publication date	Sep 30, 2025
Grant date	Sep 30, 2025

Abstract

Two dimensional images are converted to a 3D neural radiance field (NeRF), which is modified based on text personalized to a player and input to resemble the accoutrement for a character demanded by the text. A model scores how well an image matches a line of text to produce a final 3D NeRF, which may be converted to a polygonal mesh and imported into a computer simulation such as a computer game.

First claim

What is claimed is:

1. 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:
generate, using a neural radiance field (NeRF) model, a base three dimensional (3D) asset from a plurality of two dimensional (2D) images;
generate text input based on at least one of user information about a user of the base 3D asset or game information about a video game presenting the base 3D asset;
use the text input to a Contrastive Language-Image Pre-training (CLIP) model to generate a modified 3D asset from the base 3D asset; and
convert the modified 3D asset to a polygonal mesh representing a virtual character accoutrement for presentation of the virtual character accoutrement in at least one computer simulation; and
cause the modified 3D asset to be presented on a display.

2. The device of claim 1 , wherein the CLIP model rates an image match to the text input.

3. The device of claim 2 , wherein the text input is derived from player information.

4. The device of claim 3 , wherein the player information comprises a title of at least one computer simulation.

5. The device of claim 1 , wherein the text input describes a character accoutrement.

6. The device of claim 5 , wherein the character accoutrement comprises a mask.

7. The device of claim 1 , wherein the instructions are executable to: generate the text input from a starting phrase using learned ensuing phrases.

8. The device of claim 1 , comprising the at least one processor.

9. The device of claim 1 , wherein the text input is based on interaction information about a user's answers to questions about the base 3D asset.

10. A method, comprising:
generating, using a neural radiance field (NeRF) model, a base three dimensional (3D) asset from a plurality of two dimensional (2D) images;
generating text input based on at least one of user information about a user of the base 3D asset or game information about a video game presenting the base 3D asset;
using the text input to a Contrastive Language-Image Pre-training (CLIP) model to generate a modified 3D asset from the base 3D asset; and
converting the modified 3D asset to a polygonal mesh representing a virtual character accoutrement for presentation of the virtual character accoutrement in at least one computer simulation; and
causing the modified 3D asset to be presented on a display.

11. The method of claim 10 , wherein the CLIP model rates an image match to the text input.

12. The method of claim 11 , wherein the text input is derived from player information.

13. The method of claim 12 , wherein the player information comprises a title of at least one computer simulation.

14. The method of claim 10 , wherein the text input describes a character accoutrement.

15. The method of claim 14 , wherein the character accoutrement comprises a mask.

16. The method of claim 10 , further comprising:
generating the text input from a starting phrase using learned ensuing phrases.

17. The method of claim 10 , comprising at least one processor.

18. The method of claim 10 , wherein the text input is based on interaction information about a user's answers to questions about the base 3D asset.

19. A non-transitory computer-readable medium storing a plurality of instructions that, when executed by one or more processors of a computing device, cause the one or more processors to perform operations to:
generate, using a neural radiance field (NeRF) model, a base three dimensional (3D) asset from a plurality of two dimensional (2D) images;
generate text input based on at least one of user information about a user of the base 3D asset or game information about a video game presenting the base 3D asset;
use the text input to a Contrastive Language-Image Pre-training (CLIP) model to generate a modified 3D asset from the base 3D asset; and
convert the modified 3D asset to a polygonal mesh representing a virtual character accoutrement for presentation of the virtual character accoutrement in at least one computer simulation; and
cause the modified 3D asset to be presented on a display.

20. The non-transitory computer-readable medium of claim 19 , wherein the operations further comprise the CLIP model rating an image match to the text input.

Assignees

• Sony Interactive Entertainment LLC

Inventors

• Olson Joseph Logan
• Leduc Mathieu
• Masson Frederic

Classifications

• G06T17/20

  Finite element generation, e.g. wire-frame surface description, {tesselation} · CPC title

• A63F13/52

  involving aspects of the displayed game scene · CPC title

• A63F13/67

  adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use · CPC title

• A63F13/69 Primary

  by enabling or updating specific game elements, e.g. unlocking hidden features, items, levels or versions · CPC title

• G06T2219/2008

  Assembling, disassembling · CPC title