IP Library Granted Patent US 12,374,032
Granted Patent B2
US 12,374,032 · App. 17/966,212 · Granted Jul 29, 2025

Interactive image generation

Inventors: Clarence Chui (Los Altos Hills, CA); Manu Parmar (Sunnyvale, CA); Marc Mignard (Los Gatos, CA); Avinash Venkata Uppuluri (Sunnyvale, CA); Jodhvir Singh Chahal (Livermore, CA); John Le (Santa Clara, CA)
Assignee: Outward, Inc.
G06T15/506G06T7/10G06T7/50G06T7/70G06T15/04G06T15/50G06T15/60G06T17/20G06T19/006G06T19/20G06V10/70G06V20/20G06V20/36G06T2200/08G06T2200/24G06T2207/10028G06T2207/20081G06T2207/20084G06T2207/20212G06T2207/30244G06T2210/04G06T2210/56G06T2219/2004G06T2219/2016
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 12,374,032
App. No.
17/966,212
Filed
Oct 14, 2022
Granted
Jul 29, 2025
Kind
B2
Art Unit
2488
USPC
348/46
Abstract

A content generation platform is generally described herein. More specifically, interactive image generation and techniques and features thereof are disclosed herein. One or more sets of images of a scene are captured in an imaging studio. The captured one or more sets of images of the scene are processed using one or more machine learning based networks to generate an interactive image of the scene comprising a plurality of interactive features. One or more of the plurality of interactive features of the generated interactive image may be modified or edited according to user preferences.

Claims (63)

1. An imaging studio, comprising:

one or more cameras configured to capture one or more sets of images of a scene; and

one or more lighting arrays configured to provide different lighting conditions during capture of the one or more sets of images of the scene;

wherein the captured one or more sets of images of the scene are processed using one or more machine learning based networks to generate a flexible and interactive output image of the scene comprising a plurality of interactive features modifiable by an end user according to user preferences and wherein the generated flexible and interactive output image of the scene comprises a two-dimensional image with at least partial three-dimensional capabilities but without having an underlying three-dimensional model.

2. The imaging studio of claim 1 , wherein the imaging studio comprises a known and controlled physical imaging environment.

3. The imaging studio of claim 1 , wherein the imaging studio comprises an enclosure with surfaces constructed from white materials.

4. The imaging studio of claim 1 , further comprising a display or a projector to guide object placement in the imaging studio.

5. The imaging studio of claim 1 , further comprising a turntable to capture different views of the scene or parts thereof.

6. The imaging studio of claim 1 , wherein a capture application running on a computing device situated outside the imaging studio is configured to control imaging taking place within the imaging studio.

7. The imaging studio of claim 1 , wherein a capture application running on a computing device situated outside the imaging studio is configured to control various components comprising the imaging studio.

8. The imaging studio of claim 1 , wherein the one or more cameras are movable along one or more axes.

9. The imaging studio of claim 1 , wherein the one or more cameras comprise a pair of cameras for stereo captures.

10. The imaging studio of claim 1 , wherein a lighting array of the one or more lighting arrays comprises a plurality of lighting panels or boards.

11. The imaging studio of claim 1 , wherein a lighting array of the one or more lighting arrays comprises a plurality of light-emitting diodes.

12. The imaging studio of claim 1 , wherein the one or more lighting arrays or parts thereof are selectively activated for different captures to obtain image data that shows how different lighting interacts with the scene being captured in different ways.

13. The imaging studio of claim 1 , wherein the generated flexible and interactive output image is indistinguishable from imagery generated using physically based rendering techniques and underlying three-dimensional models.

14. The imaging studio of claim 1 , wherein the one or more sets of images of the scene comprise one or more different views of the scene.

15. The imaging studio of claim 1 , wherein a set of images of the one or more sets of images of the scene comprises images captured with different camera poses.

16. The imaging studio of claim 1 , wherein a set of images of the one or more sets of images of the scene comprises images captured with different lighting conditions.

17. The imaging studio of claim 1 , wherein the one or more machine learning based networks are trained at least in part on training images constrained to a prescribed scene type to which the scene belongs.

18. The imaging studio of claim 1 , wherein the generated flexible and interactive output image comprises a merging of actual reality captured with the one or more cameras and virtual reality generated using the one or more machine learning based networks.

19. A method, comprising:

configuring one or more cameras to capture one or more sets of images of a scene; and

configuring one or more lighting arrays to provide different lighting conditions during capture of the one or more sets of images of the scene;

wherein the captured one or more sets of images of the scene are processed using one or more machine learning based networks to generate a flexible and interactive output image of the scene comprising a plurality of interactive features modifiable by an end user according to user preferences and wherein the generated flexible and interactive output image of the scene comprises a two-dimensional image with at least partial three-dimensional capabilities but without having an underlying three-dimensional model.

20. A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:

configuring one or more cameras to capture one or more sets of images of a scene; and

configuring one or more lighting arrays to provide different lighting conditions during capture of the one or more sets of images of the scene;

wherein the captured one or more sets of images of the scene are processed using one or more machine learning based networks to generate a flexible and interactive output image of the scene comprising a plurality of interactive features modifiable by an end user according to user preferences and wherein the generated flexible and interactive output image of the scene comprises a two-dimensional image with at least partial three-dimensional capabilities but without having an underlying three-dimensional model.

21. The method of claim 19 , wherein the one or more sets of images of the scene are captured in an imaging studio comprising a known and controlled physical imaging environment.

22. The method of claim 19 , wherein the one or more sets of images of the scene are captured in an imaging studio comprising an enclosure with surfaces constructed from white materials.

23. The method of claim 19 , further comprising configuring a display or a projector to guide placement of one or more objects comprising the scene.

24. The method of claim 19 , further comprising configuring a turntable to capture different views of the scene or parts thereof.

25. The method of claim 19 , further comprising configuring a capture application to control imaging of the scene.

26. The method of claim 19 , further comprising configuring a capture application to control various components used to image the scene.

27. The method of claim 19 , wherein the one or more cameras are movable along one or more axes.

28. The method of claim 19 , wherein the one or more cameras comprise a pair of cameras for stereo captures.

29. The method of claim 19 , wherein a lighting array of the one or more lighting arrays comprises a plurality of lighting panels or boards.

30. The method of claim 19 , wherein a lighting array of the one or more lighting arrays comprises a plurality of light-emitting diodes.

31. The method of claim 19 , wherein the one or more lighting arrays or parts thereof are selectively activated for different captures to obtain image data that shows how different lighting interacts with the scene being captured in different ways.

32. The method of claim 19 , wherein the generated flexible and interactive output image is indistinguishable from imagery generated using physically based rendering techniques and underlying three-dimensional models.

33. The method of claim 19 , wherein the one or more sets of images of the scene comprise one or more different views of the scene.

34. The method of claim 19 , wherein a set of images of the one or more sets of images of the scene comprises images captured with different camera poses.

35. The method of claim 19 , wherein a set of images of the one or more sets of images of the scene comprises images captured with different lighting conditions.

36. The method of claim 19 , wherein the one or more machine learning based networks are trained at least in part on training images constrained to a prescribed scene type to which the scene belongs.

37. The method of claim 19 , wherein the generated flexible and interactive output image comprises a merging of actual reality captured with the one or more cameras and virtual reality generated using the one or more machine learning based networks.

38. The computer program product of claim 20 , wherein the one or more sets of images of the scene are captured in an imaging studio comprising a known and controlled physical imaging environment.

39. The computer program product of claim 20 , wherein the one or more sets of images of the scene are captured in an imaging studio comprising an enclosure with surfaces constructed from white materials.

40. The computer program product of claim 20 , further comprising computer instructions for configuring a display or a projector to guide placement of one or more objects comprising the scene.

41. The computer program product of claim 20 , further comprising computer instructions for configuring a turntable to capture different views of the scene or parts thereof.

42. The computer program product of claim 20 , wherein the computer program product comprises a capture application configured to control imaging of the scene.

43. The computer program product of claim 20 , wherein the computer program product comprises a capture application configured to control various components used to image the scene.

44. The computer program product of claim 20 , wherein the one or more cameras are movable along one or more axes.

45. The computer program product of claim 20 , wherein the one or more cameras comprise a pair of cameras for stereo captures.

46. The computer program product of claim 20 , wherein a lighting array of the one or more lighting arrays comprises a plurality of lighting panels or boards.

47. The computer program product of claim 20 , wherein a lighting array of the one or more lighting arrays comprises a plurality of light-emitting diodes.

48. The computer program product of claim 20 , wherein the one or more lighting arrays or parts thereof are selectively activated for different captures to obtain image data that shows how different lighting interacts with the scene being captured in different ways.

49. The computer program product of claim 20 , wherein the generated flexible and interactive output image is indistinguishable from imagery generated using physically based rendering techniques and underlying three-dimensional models.

50. The computer program product of claim 20 , wherein the one or more sets of images of the scene comprise one or more different views of the scene.

51. The computer program product of claim 20 , wherein a set of images of the one or more sets of images of the scene comprises images captured with different camera poses.

52. The computer program product of claim 20 , wherein a set of images of the one or more sets of images of the scene comprises images captured with different lighting conditions.

53. The computer program product of claim 20 , wherein the one or more machine learning based networks are trained at least in part on training images constrained to a prescribed scene type to which the scene belongs.

54. The computer program product of claim 20 , wherein the generated flexible and interactive output image comprises a merging of actual reality captured with the one or more cameras and virtual reality generated using the one or more machine learning based networks.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 13, 2023
From: CHUI, CLARENCE; PARMAR, MANU; MIGNARD, MARC; UPPULURI, AVINASH VENKATA; CHAHAL, JODHVIR SINGH; LE, JOHN
To: OUTWARD, INC.
Reel/Frame 062957/0983 →
Continuity (2)
Provisional Application 63255886 · Oct 14, 2021
Related Publication 20230124190A1 · Apr 20, 2023
References Cited (103)
US 6034739A · Rohlfing · 2000 [cited by applicant]
US 7420555B1 · Lee · 2008 [cited by applicant]
US 8010906B1 · Sinnard · 2011 [cited by applicant]
US 8301022B1 · McGuire · 2012 [cited by applicant]
US 9495796B2 · Breton · 2016 [cited by applicant]
US 9536340B2 · Loberg · 2017 [cited by applicant]
US 9552674B1 · Jayadevaprakash · 2017 [cited by applicant]
US 9619931B1 · Klabunde · 2017 [cited by applicant]
US 9990760B2 · Aguilera Perez · 2018 [cited by applicant]
US 10109107B2 · Knorr · 2018 [cited by applicant]
US 10127727B1 · Yuan · 2018 [cited by examiner]
US 10168789B1 · Soto · 2019 [cited by examiner]
US 10210664B1 · Chaturvedi · 2019 [cited by applicant]
US 10373380B2 · Kutliroff · 2019 [cited by applicant]
US 10692277B1 · Sunkavalli · 2020 [cited by applicant]
US 10699488B1 · Terrano · 2020 [cited by examiner]
US 10885701B1 · Patel · 2021 [cited by applicant]
US 11375179B1 · Clemens · 2022 [cited by applicant]
US 11496691B2 · Chapman · 2022 [cited by applicant]
US 11666825B2 · Delamont · 2023 [cited by examiner]
US 11856674B1 · Sanchez · 2023 [cited by applicant]
US 11864285B2 · Beaumier · 2024 [cited by applicant]
US 20010032062A1 · Plaskoff · 2001 [cited by applicant]
US 20030038875A1 · Ivanov · 2003 [cited by applicant]
US 20030174286A1 · Trumbull · 2003 [cited by applicant]
US 20040095474A1 · Matsufune · 2004 [cited by applicant]
US 20050104966A1 · Schoelkopf · 2005 [cited by applicant]
US 20070057815A1 · Foy · 2007 [cited by applicant]
US 20070133880A1 · Sun · 2007 [cited by applicant]
US 20100158379A1 · Hatfield · 2010 [cited by applicant]
US 20110242334A1 · Wilburn · 2011 [cited by applicant]
US 20120002871A1 · Hu · 2012 [cited by applicant]
US 20130218714A1 · Watkins · 2013 [cited by applicant]
US 20130272609A1 · Sun · 2013 [cited by applicant]
US 20140129990A1 · Xin · 2014 [cited by applicant]
US 20140368530A1 · James · 2014 [cited by applicant]
US 20150062125A1 · Aguilera Perez · 2015 [cited by applicant]
US 20150130790A1 · Vasquez, II · 2015 [cited by applicant]
US 20150250041A1 · Jobe · 2015 [cited by applicant]
US 20150302116A1 · Howell · 2015 [cited by applicant]
US 20160180419A1 · Adeyoola · 2016 [cited by applicant]
US 20160180441A1 · Hasan · 2016 [cited by applicant]
US 20160260260A1 · Fei · 2016 [cited by examiner]
US 20170064214A1 · Zhang · 2017 [cited by applicant]
US 20170103584A1 · Vats · 2017 [cited by applicant]
US 20180189974A1 · Clark · 2018 [cited by applicant]
US 20180255290A1 · Holzer · 2018 [cited by examiner]
US 20190043243A1 · Chui · 2019 [cited by applicant]
US 20190102949A1 · Sheftel · 2019 [cited by applicant]
US 20190121522A1 · Davis · 2019 [cited by examiner]
US 20190227172A1 · Schaefer · 2019 [cited by applicant]
US 20190227419A1 · McNelley · 2019 [cited by applicant]
US 20190318542A1 · Sai Krishna · 2019 [cited by examiner]
US 20200005448A1 · Subramanian · 2020 [cited by applicant]
US 20200098122A1 · Dal Mutto · 2020 [cited by applicant]
US 20200134383A1 · Rhee · 2020 [cited by applicant]
US 20200175759A1 · Russell · 2020 [cited by examiner]
US 20200279364A1 · Sarkisian · 2020 [cited by applicant]
US 20200302681A1 · Totty · 2020 [cited by applicant]
US 20200302686A1 · Totty · 2020 [cited by applicant]
US 20200312042A1 · Sardari · 2020 [cited by applicant]
US 20200394849A1 · Barker · 2020 [cited by applicant]
US 20200410725A1 · Haines · 2020 [cited by applicant]
US 20210012561A1 · Sunkavalli · 2021 [cited by applicant]
US 20210042950A1 · Wantland · 2021 [cited by applicant]
US 20210049811A1 · Fedyukov · 2021 [cited by applicant]
US 20210142497A1 · Pugh · 2021 [cited by applicant]
US 20210174604A1 · Long · 2021 [cited by applicant]
US 20210183080A1 · Hoiem · 2021 [cited by applicant]
US 20210201526A1 · Moloney · 2021 [cited by applicant]
US 20210224889A1 · Colby · 2021 [cited by applicant]
US 20210241478A1 · Putman · 2021 [cited by applicant]
US 20210279957A1 · Eder · 2021 [cited by applicant]
US 20210350634A1 · Major · 2021 [cited by examiner]
US 20210407169A1 · Swann · 2021 [cited by applicant]
US 20220005099A1 · Mordovskoi · 2022 [cited by applicant]
US 20220028159A1 · Vincent · 2022 [cited by applicant]
US 20220084296A1 · Sadalgi · 2022 [cited by applicant]
US 20220101507A1 · Tournier · 2022 [cited by applicant]
US 20220101556A1 · Zhang · 2022 [cited by applicant]
US 20220114291A1 · Li · 2022 [cited by applicant]
US 20220165023A1 · Lino · 2022 [cited by applicant]
US 20220269888A1 · Stoeva · 2022 [cited by applicant]
US 20220284551A1 · Neofytou · 2022 [cited by applicant]
US 20220327886A1 · Mathur · 2022 [cited by applicant]
US 20220343591A1 · Jutan · 2022 [cited by applicant]
US 20220366263A1 · Ji · 2022 [cited by applicant]
US 20230022108A1 · Ghosh · 2023 [cited by applicant]
US 20230079580A1 · Russell · 2023 [cited by applicant]
US 20230085518A1 · Chen · 2023 [cited by applicant]
US 20230093087A1 · Babinowich · 2023 [cited by applicant]
US 20230104172A1 · Kikuchi · 2023 [cited by applicant]
US 20230124190A1 · Chui · 2023 [cited by examiner]
US 20230134130A1 · Robert · 2023 [cited by applicant]
US 20230154395A1 · McNelley · 2023 [cited by applicant]
US 20230260236A1 · Rump · 2023 [cited by applicant]
US 20240037769A1 · Atwood · 2024 [cited by applicant]
US 20240090795A1 · Heng · 2024 [cited by applicant]
Sadalgi et al., U.S. Appl. No. 63/079,429 of PG Pub No. 2022/0084296 A1, filed Sep. 16, 2020. [cited by applicant]
Yang et al., “3D Object Relighting Based on Multi-View Stereo and Image Based Lighting Techniques” 2009 IEEE International Conference on Multimedia and Expo, IEEE, 2009. [cited by applicant]
Chen et al., Deep Learning Approach to Point Cloud Scene Understanding for Automated Scan to 3D Reconstruction, Journal of Computing in Civil Engineering, vol. 33, Issue 4, May 2019, 19 pages. [cited by applicant]
Havran et al., Interactive System for Dynamic Scene Lighting using Captured Video Environment Maps, Eurographics Symposium on Rendering, 2005, 14 pages. [cited by applicant]
Nguyen et al., A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation, IEEE Transactions on Visualization and Computer Graphics, vol. 24, No. 12, Dec. 2018, pp. 3005-3018. [cited by applicant]