IP Library › Granted Patent US 12,347,026
Granted Patent B2
US 12,347,026 · App. 17/966,328 · Granted Jul 1, 2025

Interactive image generation

Inventors: Marc Mignard (Los Gatos, CA); Clarence Chui (Los Altos Hills, CA); Manu Parmar (Sunnyvale, CA); Avinash Venkata Uppuluri (Sunnyvale, CA); John Le (Santa Clara, CA)
Assignee: Outward, Inc.
G06T15/506G06T7/10G06T7/50G06T7/70G06T15/04G06T15/50G06T15/60G06T17/20G06T19/006G06T19/20G06V10/70G06V20/20G06V20/36H04N23/74G06T2200/08G06T2200/24G06T2207/10028G06T2207/20081G06T2207/20084G06T2207/20212G06T2207/30244G06T2210/04G06T2210/56G06T2219/2004G06T2219/2016
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 12,347,026
App. No.
17/966,328
Filed
Oct 14, 2022
Granted
Jul 1, 2025
Kind
B2
Examiner
GRAY, RYAN M
Art Unit
2611
USPC
345/426
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 (65)

1. A method, comprising:

activating one or more cameras to sequentially capture a set of images of a prescribed view of a scene in an imaging studio; and

selectively activating different lighting panels in the imaging studio when sequentially capturing images comprising the set so that images comprising the set comprise different lighting effects;

wherein the set of images is used to at least in part generate an interactive image of the scene comprising a plurality of interactive features modifiable by an end user according to user preferences and wherein the interactive image comprises a two-dimensional image with at least partial three-dimensional capabilities including one or more options for modifying lighting.

2. The method of claim 1 , wherein images comprising the set comprise different shadow effects.

3. The method of claim 1 , wherein the interactive image of the scene comprises one or more options for modifying shadow effects.

4. The method of claim 1 , wherein the one or more cameras are stationary while sequentially capturing the set of images.

5. The method of claim 1 , wherein the one or more cameras comprise a pair of stereo cameras.

6. The method of claim 1 , wherein lighting information is extracted from the set of images using one or more machine learning based networks trained at least in part on training images constrained to a prescribed scene type to which the scene belongs.

7. The method of claim 6 , wherein lighting extracted from the set of images is blended or mixed to generate virtual lighting with respect to the interactive image.

8. The method of claim 1 , wherein shadows are extracted from the set of images using one or more machine learning based networks trained at least in part on training images constrained to a prescribed scene type to which the scene belongs.

9. The method of claim 8 , wherein shadows extracted from the set of images are blended or mixed to generate virtual shadows with respect to the interactive image.

10. The method of claim 1 , wherein one or more machine learning based networks facilitate providing virtual lighting and shadow effects with respect to the interactive image.

11. The method of claim 1 , wherein modifying lighting in the interactive image results in a dynamically provided output image with consistent lighting.

12. The method of claim 1 , wherein modifying shadows in the interactive image results in a dynamically provided output image with consistent shadows.

13. The method of claim 1 , wherein modifying a background or an environment of the interactive image results in a dynamically provided output image that appears naturally composed with consistent lighting and shadows.

14. The method of claim 1 , wherein one or more options for modifying lighting comprise a relighting feature with respect to the interactive image.

15. The method of claim 1 , wherein one or more options for modifying lighting comprise a relighting model with respect to the interactive image.

16. The method of claim 1 , wherein one or more options for modifying lighting comprise one or more options for: modifying lights, modifying light positions, and modifying light intensities.

17. The method of claim 1 , wherein one or more options for modifying lighting are provided with respect to a user application for manipulating or modifying the generated interactive image.

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

19. A system, comprising:

a processor configured to:

activate one or more cameras to sequentially capture a set of images of a prescribed view of a scene in an imaging studio; and

selectively activate different lighting panels in the imaging studio when sequentially capturing images comprising the set so that images comprising the set comprise different lighting effects; and

a memory coupled to the processor and configured to provide the processor with instructions;

wherein the set of images is used to at least in part generate an interactive image of the scene comprising a plurality of interactive features modifiable by an end user according to user preferences and wherein the interactive image comprises a two-dimensional image with at least partial three-dimensional capabilities including one or more options for modifying lighting.

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

activating one or more cameras to sequentially capture a set of images of a prescribed view of a scene in an imaging studio; and

selectively activating different lighting panels in the imaging studio when sequentially capturing images comprising the set so that images comprising the set comprise different lighting effects;

wherein the set of images is used to at least in part generate an interactive image of the scene comprising a plurality of interactive features modifiable by an end user according to user preferences and wherein the interactive image comprises a two-dimensional image with at least partial three-dimensional capabilities including one or more options for modifying lighting.

21. The system of claim 19 , wherein images comprising the set comprise different shadow effects.

22. The system of claim 19 , wherein the interactive image of the scene comprises one or more options for modifying shadow effects.

23. The system of claim 19 , wherein the one or more cameras are stationary while sequentially capturing the set of images.

24. The system of claim 19 , wherein the one or more cameras comprise a pair of stereo cameras.

25. The system of claim 19 , wherein lighting information is extracted from the set of images using one or more machine learning based networks trained at least in part on training images constrained to a prescribed scene type to which the scene belongs.

26. The system of claim 25 , wherein lighting extracted from the set of images is blended or mixed to generate virtual lighting with respect to the interactive image.

27. The system of claim 19 , wherein shadows are extracted from the set of images using one or more machine learning based networks trained at least in part on training images constrained to a prescribed scene type to which the scene belongs.

28. The system of claim 27 , wherein shadows extracted from the set of images are blended or mixed to generate virtual shadows with respect to the interactive image.

29. The system of claim 19 , wherein one or more machine learning based networks facilitate providing virtual lighting and shadow effects with respect to the interactive image.

30. The system of claim 19 , wherein modifying lighting in the interactive image results in a dynamically provided output image with consistent lighting.

31. The system of claim 19 , wherein modifying shadows in the interactive image results in a dynamically provided output image with consistent shadows.

32. The system of claim 19 , wherein modifying a background or an environment of the interactive image results in a dynamically provided output image that appears naturally composed with consistent lighting and shadows.

33. The system of claim 19 , wherein one or more options for modifying lighting comprise a relighting feature with respect to the interactive image.

34. The system of claim 19 , wherein one or more options for modifying lighting comprise a relighting model with respect to the interactive image.

35. The system of claim 19 , wherein one or more options for modifying lighting comprise one or more options for: modifying lights, modifying light positions, and modifying light intensities.

36. The system of claim 19 , wherein one or more options for modifying lighting are provided with respect to a user application for manipulating or modifying the generated interactive image.

37. The system of claim 19 , wherein the imaging studio comprises a known and controlled physical imaging environment.

38. The computer program product of claim 20 , wherein images comprising the set comprise different shadow effects.

39. The computer program product of claim 20 , wherein the interactive image of the scene comprises one or more options for modifying shadow effects.

40. The computer program product of claim 20 , wherein the one or more cameras are stationary while sequentially capturing the set of images.

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

42. The computer program product of claim 20 , wherein lighting information is extracted from the set of images using one or more machine learning based networks trained at least in part on training images constrained to a prescribed scene type to which the scene belongs.

43. The computer program product of claim 42 , wherein lighting extracted from the set of images is blended or mixed to generate virtual lighting with respect to the interactive image.

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

45. The computer program product of claim 44 , wherein shadows extracted from the set of images are blended or mixed to generate virtual shadows with respect to the interactive image.

46. The computer program product of claim 20 , wherein one or more machine learning based networks facilitate providing virtual lighting and shadow effects with respect to the interactive image.

47. The computer program product of claim 20 , wherein modifying lighting in the interactive image results in a dynamically provided output image with consistent lighting.

48. The computer program product of claim 20 , wherein modifying shadows in the interactive image results in a dynamically provided output image with consistent shadows.

49. The computer program product of claim 20 , wherein modifying a background or an environment of the interactive image results in a dynamically provided output image that appears naturally composed with consistent lighting and shadows.

50. The computer program product of claim 20 , wherein one or more options for modifying lighting comprise a relighting feature with respect to the interactive image.

51. The computer program product of claim 20 , wherein one or more options for modifying lighting comprise a relighting model with respect to the interactive image.

52. The computer program product of claim 20 , wherein one or more options for modifying lighting comprise one or more options for: modifying lights, modifying light positions, and modifying light intensities.

53. The computer program product of claim 20 , wherein one or more options for modifying lighting are provided with respect to a user application for manipulating or modifying the generated interactive image.

54. The computer program product of claim 20 , wherein the imaging studio comprises a known and controlled physical imaging environment.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 24, 2023
From: MIGNARD, MARC; CHUI, CLARENCE; PARMAR, MANU; UPPULURI, AVINASH VENKATA; LE, JOHN
To: OUTWARD, INC.
Reel/Frame 062799/0969 →
Continuity (2)
Provisional Application 63255886 · Oct 14, 2021
Related Publication 20230120613A1 · Apr 20, 2023
References Cited (104)
US 6034739A · Rohlfing · 2000 [cited by examiner]
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 examiner]
US 9536340B2 · Loberg · 2017 [cited by examiner]
US 9552674B1 · Jayadevaprakash · 2017 [cited by examiner]
US 9619931B1 · Klabunde · 2017 [cited by examiner]
US 9990760B2 · Aguilera Perez et al. · 2018 [cited by applicant]
US 10109107B2 · Knorr · 2018 [cited by examiner]
US 10127727B1 · Yuan · 2018 [cited by applicant]
US 10168789B1 · Soto · 2019 [cited by applicant]
US 10210664B1 · Chaturvedi · 2019 [cited by examiner]
US 10373380B2 · Kutliroff · 2019 [cited by applicant]
US 10692277B1 · Sunkavalli · 2020 [cited by examiner]
US 10699488B1 · Terrano · 2020 [cited by examiner]
US 10885701B1 · Patel · 2021 [cited by examiner]
US 11375179B1 · Clemens · 2022 [cited by examiner]
US 11496691B2 · Chapman · 2022 [cited by examiner]
US 11666825B2 · Delamont · 2023 [cited by applicant]
US 11856674B1 · Sanchez · 2023 [cited by applicant]
US 11864285B2 · Beaumier · 2024 [cited by examiner]
US 20010032062A1 · Plaskoff · 2001 [cited by applicant]
US 20030038875A1 · Ivanov · 2003 [cited by applicant]
US 20030174286A1 · Trumbull · 2003 [cited by examiner]
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 examiner]
US 20120002871A1 · Hu · 2012 [cited by applicant]
US 20130218714A1 · Watkins · 2013 [cited by examiner]
US 20130272609A1 · Sun · 2013 [cited by applicant]
US 20140129990A1 · Xin · 2014 [cited by applicant]
US 20140368530A1 · James · 2014 [cited by examiner]
US 20150062125A1 · Aguilera Perez · 2015 [cited by applicant]
US 20150130790A1 · Vasquez, II · 2015 [cited by applicant]
US 20150250041A1 · Jobe · 2015 [cited by examiner]
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 applicant]
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 applicant]
US 20190043243A1 · Chui · 2019 [cited by applicant]
US 20190102949A1 · Sheftel · 2019 [cited by examiner]
US 20190121522A1 · Davis · 2019 [cited by applicant]
US 20190227172A1 · Schaefer · 2019 [cited by applicant]
US 20190227419A1 · McNelley · 2019 [cited by examiner]
US 20190318542A1 · Sai Krishna · 2019 [cited by applicant]
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 applicant]
US 20200279364A1 · Sarkisian · 2020 [cited by applicant]
US 20200302681A1 · Totty · 2020 [cited by examiner]
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 examiner]
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 examiner]
US 20210241478A1 · Putman · 2021 [cited by applicant]
US 20210279957A1 · Eder · 2021 [cited by applicant]
US 20210350634A1 · Major · 2021 [cited by applicant]
US 20210407169A1 · Swann · 2021 [cited by applicant]
US 20220005099A1 · Mordovskoi · 2022 [cited by examiner]
US 20220028159A1 · Vincent · 2022 [cited by examiner]
US 20220084296A1 · Sadalgi · 2022 [cited by examiner]
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 examiner]
US 20220269888A1 · Stoeva · 2022 [cited by applicant]
US 20220284551A1 · Neofytou · 2022 [cited by examiner]
US 20220327886A1 · Mathur · 2022 [cited by applicant]
US 20220343591A1 · Jutan · 2022 [cited by examiner]
US 20220366263A1 · Ji · 2022 [cited by applicant]
US 20230022108A1 · Ghosh · 2023 [cited by examiner]
US 20230079580A1 · Russell · 2023 [cited by applicant]
US 20230085518A1 · Chen · 2023 [cited by examiner]
US 20230093087A1 · Babinowich · 2023 [cited by applicant]
US 20230104172A1 · Kikuchi · 2023 [cited by examiner]
US 20230134130A1 · Robert · 2023 [cited by examiner]
US 20230154395A1 · McNelley · 2023 [cited by examiner]
US 20230260236A1 · Rump · 2023 [cited by examiner]
US 20240037769A1 · Atwood · 2024 [cited by applicant]
US 20240087267A1 · Maschmeyer · 2024 [cited by examiner]
US 20240090795A1 · Heng · 2024 [cited by applicant]
US 20240311889A1 · Levy · 2024 [cited by examiner]
Yang, Guangwei, and Yebin Liu. “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 examiner]
Havran et al., Interactive System for Dynamic Scene Lighting using Captured Video Environment Maps, Eurographics Symposium on Rendering, 2005, 14 pages. [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]
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]
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]