Video manipulation with face replacement

Patent metadata

Field	Value
Publication number	US-11710508-B2
Application number	US-202117559575-A
Country	US
Kind code	B2
Filing date	Dec 22, 2021
Priority date	Dec 29, 2016
Publication date	Jul 25, 2023
Grant date	Jul 25, 2023

Abstract

A user device provides a user interface for video manipulation with face replacement. A method of implementations includes accessing a video comprising a plurality of frames that comprise one or more faces, providing a plurality of stickers comprising alternate face graphics for the one or more faces, receiving, via a user interface of a user device, user selection of one of the stickers and a selected face of the one or more faces, accessing a plurality of face frame sequences of the video, wherein each face frame sequence is a sequence of frames of the video comprising the selected face of the one or more faces, and replacing the selected face with the selected sticker in a first face frame sequence of the plurality of face frame sequences and in a second face frame sequence of the plurality of face frame sequences.

First claim

What is claimed is:

1. A method comprising:
accessing a video comprising a plurality of frames that comprise one or more faces;
providing a plurality of stickers comprising alternate face graphics for the one or more faces;
receiving, via a user interface of a user device, user selection of one of the stickers and a selected face of the one or more faces;
accessing a plurality of face frame sequences of the video, wherein each face frame sequence is a sequence of frames of the video comprising the selected face of the one or more faces; and
replacing the selected face with the selected sticker in a first face frame sequence of the plurality of face frame sequences and in a second face frame sequence of the plurality of face frame sequences, wherein the first face frame sequence and the second face frame sequence are separated by a third face frame sequence in which the selected face is not replaced.

2. The method of claim 1 , wherein accessing the plurality of face frame sequences comprises receiving the plurality of face frame sequences from a server device.

3. The method of claim 1 , wherein each face frame sequence of the plurality of face frame sequences is a continuous sequence of frames.

4. The method of claim 1 , further comprising receiving user selection of a frame in at least one of the plurality of face frame sequences, wherein the selected frame is the first frame in a combined face frame sequence comprising a merger of selected face frame sequences of the plurality of face frame sequences.

5. The method of claim 4 , further comprising:
receiving, from a server device, a manipulated face frame sequence, wherein the selected face is replaced with the selected sticker in each frame of the manipulated face frame sequence relative to the combined face frame sequence; and
presenting the manipulated frame sequence.

6. The method of claim 4 , further comprising:
receiving selection of a second sticker; and
sending, to a server device, a user request to replace the selected face with the second sticker in each frame of the combined face frame sequence.

7. The method of claim 4 , further comprising:
receiving selection of a second sticker and a second frame, wherein the second frame is after the selected frame in the combined face frame sequence; and
sending, to a server device, a user request to replace the selected sticker with the second sticker in the second frame and each frame after the second frame in the combined face frame sequence.

8. The method of claim 4 , further comprising:
receiving selection of a second sticker and a second frame, wherein the second frame is before the selected frame in the combined face frame sequence; and
sending, to a server device, a user request to replace the selected sticker with the second sticker in the second frame and each frame between the second frame and the selected frame in the combined face frame sequence.

9. The method of claim 4 , further comprising:
providing a plurality of audio tracks;
receiving selection of one of the audio tracks; and
sending, to a server device, a request to overlay the selected audio track on the combined face frame sequence.

10. A system comprising:
a memory; and
a processor communicably coupled to the memory, the processor to:
access a video comprising a plurality of frames that comprise one or more faces;
provide a plurality of stickers comprising alternate face graphics for the one or more faces;
receive, via a user interface of a user device, user selection of one of the stickers and a selected face of the one or more faces;
access a plurality of face frame sequences of the video, wherein each face frame sequence is a sequence of frames of the video comprising the selected face of the one or more faces; and
replace the selected face with the selected sticker in a first face frame sequence of the plurality of face frame sequences and in a second face frame sequence of the plurality of face frame sequences, wherein the first face frame sequence and the second face frame sequence are separated by a third face frame sequence in which the selected face is not replaced.

11. The system of claim 10 , wherein the processor to access the plurality of face frame sequences further comprises the processor to receive the plurality of face frame sequences from a server device.

12. The system of claim 10 , wherein each face frame sequence of the plurality of face frame sequences is a continuous sequence of frames.

13. The system of claim 10 , wherein the processor is further to receive user selection of a frame in at least one of the plurality of face frame sequences, wherein the selected frame is the first frame in a combined face frame sequence comprising a merger of selected face frame sequences of the plurality of face frame sequences.

14. The system of claim 13 , wherein the processor is further to:
receive, from a server device, a manipulated face frame sequence, wherein the selected face is replaced with the selected sticker in each frame of the manipulated face frame sequence relative to the combined face frame sequence; and
present the manipulated frame sequence.

15. The system of claim 13 , wherein the processor is further to:
receive selection of a second sticker; and
send, to a server device, a user request to replace the selected face with the second sticker in each frame of the combined face frame sequence.

16. A non-transitory computer readable storage medium storing executable computer program instructions that when executed cause a processor to:
access a video comprising a plurality of frames that comprise one or more faces;
provide a plurality of stickers comprising alternate face graphics for the one or more faces;
receive, via a user interface of a user device, user selection of one of the stickers and a selected face of the one or more faces;
access a plurality of face frame sequences of the video, wherein each face frame sequence is a sequence of frames of the video comprising the selected face of the one or more faces; and
replace the selected face with the selected sticker in a first face frame sequence of the plurality of face frame sequences and in a second face frame sequence of the plurality of face frame sequences, wherein the first face frame sequence and the second face frame sequence are separated by a third face frame sequence in which the selected face is not replaced.

17. The non-transitory computer readable storage medium of claim 16 , wherein the processor to access the plurality of face frame sequences further comprises the processor to receive the plurality of face frame sequences from a server device.

18. The non-transitory computer readable storage medium of claim 16 , wherein each face frame sequence of the plurality of face frame sequences is a continuous sequence of frames.

19. The non-transitory computer readable storage medium of claim 16 , wherein the instructions further cause the processor to receive user selection of a frame in at least one of the plurality of face frame sequences, wherein the selected frame is the first frame in a combined face frame sequence comprising a merger of selected face frame sequences of the plurality of face frame sequences.

20. The non-transitory computer readable storage medium of claim 19 , wherein the instructions further cause the processor to:
receive, from a server device, a manipulated face frame sequence, wherein the selected face is replaced with the selected sticker in each frame of the manipulated face frame sequen

Assignees

• Google Llc

Inventors

• Zukerman Jokubas
• Paglia Marco
• Sager Chad
• Poes Andrew
• Clawges Maegan
• Evfimiou Ivan
• Foster Gregory
• Keene Samuel
• Gregg John
• Morse Reed

Classifications

• G11B27/036 Primary

  Insert-editing · CPC title

• G06T11/40

  Filling planar surfaces by adding surface attributes, e.g. adding colours or textures · CPC title

• G06T11/60

  Creating or editing images; Combining images with text · CPC title

• G06V10/95

  structured as a network, e.g. client-server architectures · CPC title

• G06V20/49

  Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes · CPC title