Real time painting of a video stream
AssigneeSnapchat, Inc.
InventorsYurii Monastyrshyn, Illia Tulupov
Life of this patent
Estimating the term…
Abstract
Systems, devices, media, and methods are presented for generating graphical representations within frames of a video stream in real time. The systems and methods receive a frames depicting a portion of a face, identify user input, identify positions on the portion of the face corresponding to the user input. The systems and methods generate a graphical representation of the user input linked to positions on the portion of the face and render the graphical representation within frames of the video stream in real time.
Claims20
A method, comprising:
- receiving, by one or more processors, one or more frames of a video stream, at least a portion of the one or more frames depicting at least a portion of a face;
- identifying a user input on an input device of a computing device;
- identifying one or more positions on the portion of the face corresponding to the user input;
- linking the user input to the one or more positions on the portion of the face;
- generating a graphical representation of the user input, the graphical representation of the user input linked to the one or more positions on the portion of the face;
- and
- rendering the graphical representation on the portion of the face within one or more subsequent frames of the video stream, the graphical representation presented on the portion of the face at the one or more positions.
A system, comprising:
- one or more processors;
- and
- a non-transitory processor-readable storage medium coupled to the one or more processors and storing processor executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- receiving, by one or more processors, one or more frames of a video stream, at least a portion of the one or more frames depicting at least a portion of a face;
- identifying a user input on an input device of a computing device;
- identifying one or more positions on the portion of the face corresponding to the user input;
- linking the user input to the one or more positions on the portion of the face;
- generating a graphical representation of the user input, the graphical representation of the user input linked to the one or more positions on the portion of the face;
- and
- rendering the graphical representation on the portion of the face within one or more subsequent frames of the video stream, the graphical representation presented on the portion of the face at the one or more positions.
A non-transitory processor-readable storage medium storing processor executable instructions that, when executed by a processor of a machine, cause the machine to perform operations comprising:
- receiving, by one or more processors, one or more frames of a video stream, at least a portion of the one or more frames depicting at least a portion of a face;
- identifying a user input on an input device of a computing device;
- identifying one or more positions on the portion of the face corresponding to the user input;
- linking the user input to the one or more positions on the portion of the face;
- generating a graphical representation of the user input, the graphical representation of the user input linked to the one or more positions on the portion of the face;
- and
- rendering the graphical representation on the portion of the face within one or more subsequent frames of the video stream, the graphical representation presented on the portion of the face at the one or more positions.
Dependencies are inferred from the claim text.