Dynamic mask application

Abstract

In one embodiment, a method includes receiving an indication to apply a dynamic mask to an input video, wherein the dynamic mask comprises a plurality of graphical features according to a plurality of mask effects, and wherein the dynamic mask is applied based on one or more user selections specifying one or more of the mask effects, identifying a first user in an input image, and generating an output video comprising the graphical features rendered using the mask effects.

What is claimed is: 
     
         1 . A method comprising, by one or more computing devices:
 receiving an indication to apply a dynamic mask to an input video, wherein the dynamic mask comprises a plurality of graphical features according to a plurality of mask effects, and wherein the dynamic mask is applied based on one or more user selections specifying one or more of the mask effects;   identifying a first user portrayed in the input video;   generating an output video comprising the graphical features rendered using the mask effects with respect to the portrayed first user.   
     
     
         2 . The method of  claim 1 , wherein the graphical features are rendered corresponding to movement of the portrayed first user in the input video. 
     
     
         3 . The method of  claim 1 , wherein the dynamic mask is animated corresponding to movement of the portrayed first user in the input video. 
     
     
         4 . The method of  claim 1 , wherein the graphical features comprise one or more of eyes, eyebrows, nose, mouth, teeth, hat, face painting, or facial features. 
     
     
         5 . The method of  claim 1 , further comprising:
 identifying a facial expression of the portrayed first user in the input video, and wherein the graphical features are rendered corresponding to the facial expression of the portrayed first user in the input video.   
     
     
         6 . The method of  claim 1 , wherein the input video comprises a plurality of frames, and wherein the output video is generated according to each of the plurality of frames individually. 
     
     
         7 . The method of  claim 1 , wherein the graphical features are generated by combining the portrayed first user with the plurality of mask effects according to mask instructions. 
     
     
         8 . The method of  claim 1 , wherein the plurality of graphical features are positioned in the output video at locations that are determined based on locations of corresponding facial features of the portrayed first user in the input video according to mask geometry information associated with the mask effects. 
     
     
         9 . The method of  claim 8 , wherein the mask geometry information comprises positions and shapes of the plurality of graphical features. 
     
     
         10 . The method of  claim 8 , wherein mask geometry information comprises coordinates of one or more geometric points of each of the plurality of graphical features. 
     
     
         11 . The method of  claim 10 , wherein the graphical features are animated in the output video based on modifying the coordinates of the one or more geometric points according to change in location of the corresponding facial features of the first user in the input video. 
     
     
         12 . The method of  claim 1 , wherein the input video is captured using a camera of a client device, and wherein the output video is displayed on a display of the client device. 
     
     
         13 . The method of  claim 1 , wherein the input video is received from a file. 
     
     
         14 . The method of  claim 1 , wherein the graphical features generated by the mask effects comprise one or more of exaggerated facial features, renderings of inanimate physical objects, or stylized facial features. 
     
     
         15 . One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
 receive an indication to apply a dynamic mask to an input video, wherein the dynamic mask comprises a plurality of graphical features according to a plurality of mask effects, and wherein the dynamic mask is applied based on one or more user selections specifying one or more of the mask effects;   identify a first user portrayed in the input image;   generate an output video comprising the graphical features rendered using the mask effects with respect to the portrayed first user.   
     
     
         16 . The computer-readable non-transitory storage media of  claim 15 , wherein the dynamic mask is animated corresponding to movement of the first user in the input video. 
     
     
         17 . The computer-readable non-transitory storage media of  claim 15 , wherein the graphical features comprise one or more of eyes, eyebrows, nose, mouth, teeth, hat, face painting, or facial features. 
     
     
         18 . The computer-readable non-transitory storage media of  claim 15 , the software further operable when executed to:
 identify a facial expression of the portrayed first user in the input video, and wherein the graphical features are rendered corresponding to the facial expression of the portrayed first user in the input video.   
     
     
         19 . The computer-readable non-transitory storage media of  claim 15 , wherein the plurality of graphical features are positioned in the output video at locations that are determined based on locations of corresponding facial features of the portrayed first user in the input video according to mask geometry information associated with the mask effects. 
     
     
         20 . A system comprising: one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to:
 receive an indication to apply a dynamic mask to an input video, wherein the dynamic mask comprises a plurality of graphical features according to a plurality of mask effects, and wherein the dynamic mask is applied based on one or more user selections specifying one or more of the mask effects;   identify a first user portrayed in the input image;   generate an output video comprising the graphical features rendered using the mask effects with respect to the portrayed first user.