IP Library Granted Patent US 12,079,924
Granted Patent B2
US 12,079,924 · App. 17/788,985 · Granted Sep 3, 2024

System and method for dynamic images virtualization

Inventor: Karen Abramyanc (Bat Yam, IL)
Assignee: SNAP INC.
G06T15/205G06T3/4053G06T5/50G06T5/77G06T9/00G06T2207/20021G06T2207/20081G06T2207/20084
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,079,924
App. No.
17/788,985
Granted
Sep 3, 2024
Kind
B2
Abstract

A dynamic image virtualization system and method configured to utilize an AI model in order to conduct a reduced latency real-time prediction process upon at least one input image, wherein said prediction process is designated to create free-viewpoint 3D extrapolated output dynamic images tailored in advance to the preferences or needs of a user and comprising more visual data than the at least one input image.

Claims (23)

1. A dynamic images virtualization system, comprising:

(i) a controller configured to perform digital image processing by using an AI model trained to perform data fetching prediction upon at least one input image generated by a static 2D computer generated imagery (CGI) and to create extrapolated output dynamic images that contain more visual data than the at least one input image generated by the static 2D CGI, the data fetching prediction by the AI model extracting a tile from a cache memory before detection of any indication of user viewing interest; and

(ii) at least one display means configured to present the extrapolated output dynamic images to at least one user, the extrapolated output dynamic images containing more visual data than the at least one input image by including the tile extracted by the AI model from the cache memory before detection of any indication of user viewing interest,

wherein the at least one input image is generated offline by the static 2D CGI prior to the data fetching prediction and the extrapolated output dynamic images are free viewpoint 3D images and wherein the data fetching prediction has a reduced-latency and results in production of the extrapolated output dynamic images that comprise novel images as well as novel multi-directional and image scenery parameters in comparison with the at least one input image generated offline by the static 2D CGI prior to the data fetching prediction.

2. The system of claim 1 , wherein the at least one input image is subdivided into multiple image tiles.

3. The system of claim 1 , wherein the reduced latency data fetching prediction uses a content-delivery-network (CDN) by extracting the tile from a local cache provided by the CDN.

4. The system of claim 1 , wherein the reduced latency data fetching prediction produces the extrapolated output dynamic images by calculating and generating subsequent future tiles that are based on the at least one input image.

5. The system of claim 4 , wherein each tile of the subsequent future tiles includes an array of visual data.

6. The system of claim 5 , wherein the array of visual data of each tile is compressed.

7. The system of claim 4 , wherein each tile is a multi-resolution tile.

8. The system of claim 4 , wherein each tile is a multi-view compressed tile.

9. The system of claim 4 , wherein each tile is temporally compressed.

10. The system of claim 4 , wherein each tile of the subsequent future tiles is combined with at least one other tile to create a larger tile comprising visual data of the combined tiles.

11. The system of claim 4 , wherein the extrapolated output dynamic images comprise an unrestricted stack of overlay layers and resolution pyramids.

12. The system of claim 1 , wherein the extrapolated output dynamic images provide an input to the AI model that was trained to conduct image quality enhancement using a deep neural network (DNN).

13. The system of claim 1 , wherein further image quality enhancement is performed upon the extrapolated output dynamic images using a super resolution (SP) technique.

14. The system of claim 1 , wherein the digital image processing performs streaming of object-centric volumetric content presented to the at least one user using the at least one display means.

15. The system of claim 1 , wherein the digital image processing performs streaming of view-centric volumetric content presented to the at least one user using the at least one display means.

16. The system of claim 1 , wherein the extrapolated output dynamic images are presented using unstructured light-field technology.

17. The system of claim 1 , wherein the extrapolated output dynamic images are presented using billboard based quad rendering.

18. The system of claim 1 , wherein the at least one input image is created and then displayed as extrapolated output dynamic images by using a view-dependent reconstruction of a virtual camera.

19. The system of claim 1 , wherein the extrapolated output dynamic images display at least one of a virtualized architectural space or a virtualized architectural structure.

20. The system of claim 1 , wherein the extrapolated output dynamic images display at least one virtualized visual effect.

Assignments (8)
CORRECTIVE ASSIGNMENT TO CORRECT THE REMOVE ERRONEOULSY FILED APPLICATION NUMBERS 07823814, 17893696, 17887215, 77895449, 17821431 AND 63397172 PREVIOUSLY RECORDED AT REEL: 061092 FRAME: 0669. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded May 26, 2023
From: BAE SYSTEMS PLC
To: SNAP INC.
Reel/Frame 063789/0001 →
CORRECTIVE ASSIGNMENT TO CORRECT THE REMOVE ASSIGNMENT ERRONEOUSLY FILED FOR 17788985, 17939256, 17597699, 17939296, 17597698 AND 17250997. PREVIOUSLY RECORDED AT REEL: 061092 FRAME: 0669. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Dec 7, 2022
From: BAE SYSTEMS PLC
To: SNAP INC.
Reel/Frame 062112/0237 →
CORRECTIVE ASSIGNMENT TO CORRECT THE TO REMOVE THE ASSIGNMENT ERRONEOUSLY FILED FOR APPLICATION #S 09727095, 09727132, 09737418, 09792133, 09311804, AND 09369685 PREVIOUSLY RECORDED AT REEL: 061092 FRAME: 0669. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Dec 7, 2022
From: BAE SYSTEMS PLC
To: SNAP INC.
Reel/Frame 062219/0544 →
CORRECTIVE ASSIGNMENT TO CORRECT THE REMOVE THE ASSIGNMENT ERRONEOUSLY FILED FOR APPLICATION #S 09999093, 10217152, 17815831, 60062731, AND 17823810 PREVIOUSLY RECORDED AT REEL: 061092 FRAME: 0669. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Dec 7, 2022
From: BAE SYSTEMS PLC
To: SNAP INC.
Reel/Frame 062219/0586 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 18, 2022
From: BOTTEGA STUDIOS LTD.
To: CYPRESS INVESTMENT ASSET HOLDINGS LLC
Reel/Frame 061458/0168 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 18, 2022
From: CYPRESS INVESTMENT ASSET HOLDINGS LLC
To: SNAP INC.
Reel/Frame 061458/0257 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 14, 2022
From: BAE SYSTEMS PLC
To: SNAP INC.
Reel/Frame 061092/0669 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 30, 2022
From: ABRAMYANC, KAREN
To: BOTTEGA STUDIOS LTD.
Reel/Frame 060367/0065 →