IP Library › Granted Patent US 11,562,474
Granted Patent B2
US 11,562,474 · App. 17/144,885 · Granted Jan 24, 2023

Mobile multi-camera multi-view capture

Inventors: Stefan Johannes Josef Holzer (San Mateo, CA); Abhishek Kar (Berkeley, CA); Matteo Munaro (San Francisco, CA); Pavel Hanchar (Minsk, BY); Radu Bogdan Rusu (San Francisco, CA)
Assignee: Fyusion, Inc.
G06T7/0004G06T3/4038G06T5/50G06V10/44H04N5/2258
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 11,562,474
App. No.
17/144,885
Granted
Jan 24, 2023
Kind
B2
Abstract

A background scenery portion may be identified in each of a plurality of image sets of an object, where each image set includes images captured simultaneously from different cameras. A correspondence between the image sets may determined, where the correspondence tracks control points associated with the object and present in multiple images. A multi-view interactive digital media representation of the object that is navigable in one or more dimensions and that includes the image sets may be generated and stored.

Claims (31)

1. A computing device comprising:

a plurality of cameras operable to capture a plurality of image sets of an object, each image set including a respective two or more images captured from a respective viewpoint simultaneously, each of the respective two or more images being captured by a respective one of the plurality of cameras;

a processor operable to identify a background scenery portion in each of the first plurality of image sets and determine a correspondence between the plurality of image sets, the correspondence tracking one or more control points associated with the object and present in multiple images; and

a storage device configured to store a multi-view interactive digital media representation of the object that includes the plurality of image sets, the multi-view interactive digital media representation being navigable in one or more dimensions.

2. The computing device recited in claim 1 , wherein each of the plurality of cameras is located on a mobile computing device.

3. The computing device recited in claim 2 , wherein the correspondence is determined in part via inertial data captured from an inertial measurement unit on the mobile computing device.

4. The computing device recited in claim 1 , wherein a first one of the plurality of cameras is a wide-angle lens.

5. The computing device recited in claim 4 , wherein a second one of the plurality of cameras is a telephoto lens.

6. The computing device recited in claim 1 , constructing a sub-multi-view interactive digital media representation for a designated portion of the object, the sub-multi-view interactive digital media representation including a plurality of images of the designated portion of the object, each of the plurality of images being captured from a respective one of the viewpoints.

7. The computing device recited in claim 6 , wherein the sub-multi-view interactive digital media representation is zoomed in relative to the multi-view interactive digital media representation, and wherein the sub-multi-view interactive digital media representation is navigable in one or more dimensions.

8. A method comprising:

identifying via a processor a background scenery portion in each of a plurality of image sets of an object, each image set including a respective two or more images captured from a respective viewpoint simultaneously, each of the respective two or more images being captured by a respective one of a plurality of cameras;

determining a correspondence between the plurality of image sets, the correspondence tracking one or more control points associated with the object and present in multiple images;

generating a multi-view interactive digital media representation (MVIDMR) of the object that includes the plurality of image sets, the MVIDMR being navigable in one or more dimensions; and

storing the MVIDMR on a storage device.

9. The method recited in claim 8 , wherein each of the plurality of cameras is located on a mobile computing device.

10. The method recited in claim 9 , wherein the correspondence is determined in part via inertial data captured from an inertial measurement unit on the mobile computing device.

11. The method recited in claim 8 , wherein a first one of the plurality of cameras is a wide-angle lens.

12. The method recited in claim 11 , wherein a second one of the plurality of cameras is a telephoto lens.

13. The method recited in claim 12 , constructing a sub-multi-view interactive digital media representation for a designated portion of the object, the sub-multi-view interactive digital media representation including a plurality of images of the designated portion of the object, each of the plurality of images being captured from a respective one of the viewpoints.

14. The method recited in claim 13 , wherein the sub-multi-view interactive digital media representation is zoomed in relative to the multi-view interactive digital media representation, and wherein the sub-multi-view interactive digital media representation is navigable in one or more dimensions.

15. One or more non-transitory computer readable media having instructions stored thereon for causing a computing system to perform a method, the method comprising:

identifying via a processor a background scenery portion in each of a plurality of image sets of an object, each image set including a respective two or more images captured from a respective viewpoint simultaneously, each of the respective two or more images being captured by a respective one of a plurality of cameras;

determining a correspondence between the plurality of image sets, the correspondence tracking one or more control points associated with the object and present in multiple images;

generating a multi-view interactive digital media representation (MVIDMR) of the object that includes the plurality of image sets, the MVIDMR being navigable in one or more dimensions; and

storing the MVIDMR on a storage device.

16. The one or more non-transitory computer readable media recited in claim 15 , wherein each of the plurality of cameras is located on a mobile computing device.

17. The one or more non-transitory computer readable media recited in claim 16 , wherein the correspondence is determined in part via inertial data captured from an inertial measurement unit on the mobile computing device.

18. The one or more non-transitory computer readable media recited in claim 15 , wherein a first one of the plurality of cameras is a wide-angle lens.

19. The one or more non-transitory computer readable media recited in claim 18 , wherein a second one of the plurality of cameras is a telephoto lens.

20. The one or more non-transitory computer readable media recited in claim 15 , constructing a sub-multi-view interactive digital media representation for a designated portion of the object, the sub-multi-view interactive digital media representation including a plurality of images of the designated portion of the object, each of the plurality of images being captured from a respective one of the viewpoints, wherein the sub-multi-view interactive digital media representation is zoomed in relative to the multi-view interactive digital media representation, and wherein the sub-multi-view interactive digital media representation is navigable in one or more dimensions.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 8, 2021
From: HOLZER, STEFAN JOHANNES JOSEF; KAR, ABHISHEK; MUNARO, MATTEO; HANCHAR, PAVEL; RUSU, RADU BOGDAN
To: FYUSION, INC.
Reel/Frame 054865/0052 →
Continuity (2)
Provisional Application 62961822 · Jan 16, 2020
Related Publication 20210224973A1 · Jul 22, 2021
Cited By (2)
US 12,333,710 US 12,581,196