Adjusting participant gaze in video conferences

Abstract

Methods and systems for applying gaze adjustment techniques to participants in a video conference are disclosed. Some examples may include: receiving, at computing system, image adjustment information associated with a video stream including images of a first participant, identifying, for a display layout of a communication application, a location displaying the images of the first participant, determining, based on the received image adjustment information, a location displaying images of a second participant for the display layout, the received image adjustment information indicating that an eye gaze of the first participant being directed toward the second participant, computing an eye gaze direction of the first participant based on the location displaying images of the second participant, generating gaze-adjusted images based on the desired eye gaze direction of the first participant and replacing the images within the video stream with the gaze-adjusted images.

What is claimed is: 
     
         1 . A method, comprising:
 receiving, at computing system, image adjustment information associated with a video stream including images of a first participant;   identifying, for a display layout of a communication application, a location displaying the images of the first participant;   determining, based on the received image adjustment information, a location displaying images of a second participant for the display layout, the received image adjustment information indicating that an eye gaze of the first participant being directed toward the second participant;   computing an eye gaze direction of the first participant based on the location displaying images of the second participant;   generating gaze-adjusted images based on the eye gaze direction of the first participant, wherein the gaze-adjusted images include at least one of an adjusted eye gaze direction of the first participant or an adjusted head pose of the first participant; and   replacing the images within the video stream with the gaze-adjusted images.   
     
     
         2 . The method of  claim 1 , further comprising:
 capturing, via a camera of the computing system, a second video stream including images of a user of the computing system;   detecting, via a processor of the computing system, a face region of the user within the images;   detecting facial feature regions of the user within the images based on the detected face region;   detecting an eye region of the user within the images based on the detected facial feature regions;   computing an eye gaze direction of the user based on the detected eye region;   identifying a third participant in the display layout based on the eye gaze direction of the user; and   providing gaze information to a gaze coordinator, the gaze information including an identifier associated with the user and an identifier associated with the third participant.   
     
     
         3 . The method of  claim 2 , further comprising:
 computing an eye gaze direction of the third participant based on received image adjustment information associated with a second video stream including images of the third participant;   generating second gaze-adjusted images based on the eye gaze direction of the third participant; and   replacing the images within the second video stream with the second gaze-adjusted images.   
     
     
         4 . The method of  claim 1 , further comprising:
 generating second gaze-adjusted images based on eye gaze direction of a third participant be directed toward a location other than a display device displaying a graphical user interface of the communication application, the second gaze-adjusted images including a graphic; and   replacing the images within a second video stream including images of the third participant with the second gaze-adjusted images.   
     
     
         5 . The method of  claim 1 , further comprising:
 changing an appearance of the eyes of the first participant based on estimates of a head pose; and   changing an appearance of the first participant's head and torso by rotating the first participant's head and torso to generate the gaze-adjusted images.   
     
     
         6 . The method of  claim 1 , wherein the image adjustment information is specific to a participant video stream and the computing system. 
     
     
         7 . The method of  claim 2 , wherein the user has not shared the user's video stream. 
     
     
         8 . A system, comprising:
 one or more hardware processors configured by machine-readable instructions to:   receive, at computing system, image adjustment information associated with a video stream including images of a first participant;   identify, for a display layout of a communication application, a location displaying the images of the first participant;   determine, based on the received image adjustment information, a location displaying images of a second participant for the display layout, the received image adjustment information indicating that an eye gaze of the first participant be directed toward the second participant;   compute an eye gaze direction of the first participant based on the location displaying images of the second participant;   generate gaze-adjusted images based on the eye gaze direction of the first participant, wherein the gaze-adjusted images include at least one of an adjusted eye gaze direction of the first participant or an adjusted head pose of the first participant; and   replace the images within the video stream with the gaze-adjusted images.   
     
     
         9 . The system of  claim 8 , wherein the one or more hardware processors are further configured by machine-readable instructions to:
 capture, via a camera of the computing system, a second video stream including images of a user of the computing system;   detect, via a processor of the computing system, a face region of the user within the images;   detect facial feature regions of the user within the images based on the detected face region;   detect an eye region of the user within the images based on the detected facial feature regions;   compute an eye gaze direction of the user based on the detected eye region;   identify a third participant in the display layout based on the eye gaze direction of the user; and   provide gaze information to a gaze coordinator, the gaze information including an identifier associated with the user and an identifier associated with the third participant.   
     
     
         10 . The system of  claim 9 , wherein the one or more hardware processors are further configured by machine-readable instructions to:
 compute an eye gaze direction of the third participant based on received image adjustment information associated with a second video stream including images of the third participant;   generate second gaze-adjusted images based on the eye gaze direction of the third participant; and   replace the images within the second video stream with the second gaze-adjusted images.   
     
     
         11 . The system of  claim 8 , wherein the one or more hardware processors are further configured by machine-readable instructions to:
 generate second gaze-adjusted images based on eye gaze direction of a third participant be directed toward a location other than a display device displaying a graphical user interface of the communication application, the second gaze-adjusted images including a graphic; and   replace the images within a second video stream including images of the third participant with the second gaze-adjusted images.   
     
     
         12 . The system of  claim 8 , wherein the one or more hardware processors are further configured by machine-readable instructions to:
 change an appearance of the eyes of the first participant based on estimates of a head pose; and   change an appearance of the first participant's head and torso by rotating the first participant's head and torso to generate the gaze-adjusted images.   
     
     
         13 . The system of  claim 8 , wherein the image adjustment information is specific to a participant video stream and the computing system. 
     
     
         14 . The system of  claim 9 , wherein a user of the computing system has not shared the user's video stream. 
     
     
         15 . A method for applying gaze adjustment techniques to participants in a video conference, the method comprising:
 capturing, via a camera of a computing system, a video stream including images of a user of the computing system;   detecting, via a processor of the computing system, a face region of the user within the images;   detecting facial feature regions of the user within the images based on the detected face region;   detecting an eye region of the user within the images based on the detected facial feature regions;   computing an eye gaze direction of the user based on the detected eye region;   identifying a participant in a display layout of a video communication application based on the eye gaze direction of the user; and   providing gaze information to a gaze coordinator, the gaze information including an identifier associated with the user and an identifier associated with the participant.   
     
     
         16 . The method of  claim 15 , further comprising:
 receiving, at the computing system, image adjustment information associated with a video stream including images of a second participant;   identifying, based on the display layout of the video communication application, a location displaying the images of the second participant;   determining, based on the received image adjustment information, a location displaying images of a third participant for the display layout, the received image adjustment information indicating that an eye gaze of the second participant is directed toward the third participant;   computing an eye gaze direction of the second participant based on the location displaying images of the third participant;   generating gaze-adjusted images based on the eye gaze direction of the second participant, wherein the gaze-adjusted images include at least one of an adjusted eye gaze direction of the second participant or an adjusted head pose of the second participant; and   replacing the images within the video stream with the gaze-adjusted images.   
     
     
         17 . The method of  claim 15 , further comprising:
 generating gaze-adjusted images based on an eye gaze direction of a second participant being directed toward a location other than a display device displaying a graphical user interface of the communication application, the gaze-adjusted images including a graphic; and   replacing the images within a second video stream including images of the second participant with the gaze-adjusted images.   
     
     
         18 . The method of  claim 16 , further comprising changing an appearance of the user's head and torso by rotating the user's head and torso in an image to generate the gaze-adjusted images. 
     
     
         19 . The method of  claim 16 , wherein the image adjustment information is specific to a participant video stream and the computing system. 
     
     
         20 . The method of  claim 15 , wherein the user has not shared the user's video stream.