Composited animation

Inventors: Alexis Hope Gottlieb (Somerville, MA); Daniel Joshua Steinbock (Berkeley, CA); Siyin Yang (Mercer Island, WA); Clark Scheff (Seattle, WA); Sridhar Rao (Palo Alto, CA); Alexander Charles Granieri (Palo Alto, CA); Francislav Penov (Kirkland, WA); Upendra Shardanand (Seattle, WA); Eric Erkon Hsin (Seattle, WA)

Assignee: Facebook, Inc.

G06T3/4038 G06T3/0006 G06T7/285 G06T7/292 G06T13/20 G06T13/80

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 10,275,856
App. No.: 15/668,615
Granted: Apr 30, 2019
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

In one embodiment, a method includes receiving at least two images captured by one or more cameras, wherein a first image of the at least two images has a subject and a second image of the at least two images comprises a perspective of the geographic location that is different than the first image; identifying an object that is common to the at least two images; computing a difference in perspective between the images that is based on a difference in size and shape between the object in the first image and the object in the second image; generating, based on the difference in perspective, an animation of a transition from the first image to the second image, wherein the animation comprises both the first image and the second image, and wherein the animation adds a modified version of the subject to the second image.

Claims (49)

1. A method comprising, by a server computing machine:

receiving at least two images captured by one or more cameras, wherein:

a first image of the at least two images comprises a first perspective of a subject from a first geographic location; and

a second image of the at least two images comprises a second perspective of the subject from a second geographic location that is different than the first geographic location;

identifying, from the at least two images, an object that is common to the at least two images;

computing a difference in perspective between the at least two images that is based at least in part on a difference in size and shape between the object in the first image and the object in the second image;

generating, based on the difference in perspective, a modified version of the subject;

adding, to the second image, the modified version of the subject;

generating, an animation to illustrate a transition from the first image to the second image, wherein the animation comprises both the first image and the second image; and

sending instructions to a client system of a user to display the animation on a display screen of the client system.

2. The method of claim 1 , wherein the subject is a user of an online social network, further comprising sending a message to the user that a first-degree connection of the user has received an animation associated with the first geographic location.

3. The method of claim 1 , wherein the modified version of the subject has been transformed based on the difference in perspective.

4. The method of claim 3 , wherein the transformation comprises a scaling of the subject and a tilting of the subject.

5. The method of claim 1 , wherein the first image was sent by a first user in response to a prompt sent to the first user to send an image, wherein the prompt was sent based on a user-engagement metric associated with the first geographic location.

6. The method of claim 1 , wherein the object that is common to the at least two images comprises a planar front surface that comprises a polygon.

7. The method of claim 1 , wherein the second image is a composite image created from a plurality of images posted to an online social network, wherein each image of the plurality of images comprises a perspective of the first geographic location.

8. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

receive at least two images captured by one or more cameras, wherein:

a first image of the at least two images comprises a first perspective of a subject from a first geographic location; and

a second image of the at least two images comprises a second perspective of the subject from a second geographic location that is different than the first geographic location;

identify, from the at least two images, an object that is common to the at least two images;

compute a difference in perspective between the at least two images that is based at least in part on a difference in size and shape between the object in the first image and the object in the second image;

generate, based on the difference in perspective, a modified version of the subject;

add, to the second image, the modified version of the subject;

generate, an animation to illustrate a transition from the first image to the second image, wherein the animation comprises both the first image and the second image; and

send instructions to a client system of a user to display the animation on a display screen of the client system.

9. The media of claim 8 , wherein the subject is a user of an online social network, and wherein the software is further operable when executed to send a message to the user that a first-degree connection of the user has received an animation associated with the first geographic location.

10. The media of claim 8 , wherein the modified version of the subject has been transformed based on the difference in perspective.

11. The media of claim 10 , wherein the transformation comprises a scaling of the subject and a tilting of the subject.

12. The media of claim 8 , wherein the first image was sent by a first user in response to a prompt sent to the first user to send an image, wherein the prompt was sent based on a user-engagement metric associated with the first geographic location.

13. The media of claim 8 , wherein the object that is common to the at least two images comprises a planar front surface that comprises a polygon.

14. The media of claim 8 , wherein the second image is a composite image created from a plurality of images posted to an online social network, wherein each image of the plurality of images comprises a perspective of the first geographic location.

15. A system comprising:

one or more processors; and

one or more computer-readable non-transitory storage media coupled to one or more of the processors and comprising instructions operable when executed by one or more of the processors to cause the system to: