Abstract: A illustrative method includes providing, for display by a display device, a first preview of a three-dimensional (3D) virtual reality video in a 3D object in a virtual reality menu user interface, the first preview of the 3D virtual reality video corresponding to a first location within the 3D object, receiving data describing a rotation of the 3D object in the virtual reality menu user interface, and providing, for display by the display device and based on the rotation of the 3D object, a second preview of the 3D virtual reality video in the 3D object in the virtual reality menu user interface, the second preview of the 3D virtual reality video corresponding to a second location within the 3D object.

Abstract: An illustrative volumetric capture system accesses a machine learning model associated with bodies of a particular body type, as well as a two-dimensional (2D) image captured by a capture device located at a real-world scene. The 2D image depicts a body of the particular body type that is present at the real-world scene. Using the machine learning model and based on the 2D image, the volumetric capture system identifies a 2D joint location, from a perspective of the capture device, of a particular joint of the body. The volumetric capture system also generates a three-dimensional (3D) reference model of the body that represents the particular joint of the body at a 3D joint location that is determined based on the 2D joint location identified using the machine learning model. Corresponding methods and systems are also disclosed.

Abstract: A method includes receiving two-dimensional video streams from a plurality of cameras, the two-dimensional video streams including multiple angles of a sporting event. The method further includes determining boundaries of the sporting event from the two-dimensional video streams. The method further includes identifying a location of a sporting object during the sporting event. The method further includes identifying one or more players in the sporting event. The method further includes identifying poses of each of the one or more players during the sporting event. The method further includes generating a three-dimensional model of the sporting event based on the boundaries of the sporting event, the location of the sporting object during the sporting event, and the poses of each of the one or more players during the sporting event. The method further includes generating a simulation of the three-dimensional model.

Abstract: A illustrative method includes providing, for display by a display device, a first preview of a three-dimensional (3D) virtual reality video in a 3D object in a virtual reality menu user interface, the first preview of the 3D virtual reality video corresponding to a first location within the 3D object, receiving data describing a rotation of the 3D object in the virtual reality menu user interface, and providing, for display by the display device and based on the rotation of the 3D object, a second preview of the 3D virtual reality video in the 3D object in the virtual reality menu user interface, the second preview of the 3D virtual reality video corresponding to a second location within the 3D object.

Abstract: A method includes generating a three-dimensional (3D) virtual reality video by stitching together image frames of an environment captured by a camera array. The method further includes generating graphical data for displaying a virtual reality user interface that includes the 3D virtual reality video. The method further includes determining, based on movement of a peripheral device, that a user moves a hand to be located in front of the 3D virtual reality video in the user interface and grabs the 3D virtual reality video from a first location to inside an object. The method further includes displaying the object with a preview of the 3D virtual reality video inside the object.

Abstract: A method includes generating a set of three-dimensional (3D) virtual reality videos by stitching together image frames of one or more environments captured by a camera array. The method further includes generating graphical data for displaying a virtual reality user interface that includes (1) selectable icons that correspond to the set of 3D virtual reality videos and (2) an object. The method further includes receiving, from a peripheral device, a selection of the object by a user of the peripheral device in the virtual reality user interface and an indication of a desire to move the object to be positioned in front of a first 3D virtual reality video from the set of virtual reality videos. The method further includes providing a first 3D preview of the first 3D virtual reality video within the object.

Abstract: A method includes receiving head-tracking data that describe one or more positions of people while the people are viewing a three-dimensional video. The method further includes generating a probabilistic model of the one or more positions of the people based on the head-tracking data, wherein the probabilistic model identifies a probability of a viewer looking in a particular direction as a function of time. The method further includes generating video segments from the three-dimensional video. The method further includes, for each of the video segments: determining a directional encoding format that projects latitudes and longitudes of locations of a surface of a sphere onto locations on a plane, determining a cost function that identifies a region of interest on the plane based on the probabilistic model, and generating optimal segment parameters that minimize a sum-over position for the region of interest.

Abstract: An illustrative volumetric capture system accesses a machine learning model associated with bodies of a particular body type, as well as a two-dimensional (2D) image captured by a capture device located at a real-world scene. The 2D image depicts a body of the particular body type that is present at the real-world scene. Using the machine learning model and based on the 2D image, the volumetric capture system identifies a 2D joint location, from a perspective of the capture device, of a particular joint of the body. The volumetric capture system also generates a three-dimensional (3D) reference model of the body that represents the particular joint of the body at a 3D joint location that is determined based on the 2D joint location identified using the machine learning model. Corresponding methods and systems are also disclosed.

Abstract: A method includes generating graphical data for displaying a virtual reality user interface that includes a three-dimensional (3D) virtual reality video that is illustrated as being inside a sphere. The method further includes determining, based on movement of a peripheral device, that a user selects the sphere in the virtual reality user interface and the user moves the sphere on a head of the user. The method further includes displaying the 3D virtual reality video in the sphere surrounding the head of the user such that the user views a 360 degree environment corresponding to the 3D virtual reality video.

Abstract: A method includes receiving head-tracking data that describe one or more positions of people while the people are viewing a three-dimensional video. The method further includes generating a probabilistic model of the one or more positions of the people based on the head-tracking data, wherein the probabilistic model identifies a probability of a viewer looking in a particular direction as a function of time. The method further includes generating video segments from the three-dimensional video. The method further includes, for each of the video segments: determining a directional encoding format that projects latitudes and longitudes of locations of a surface of a sphere onto locations on a plane, determining a cost function that identifies a region of interest on the plane based on the probabilistic model, and generating optimal segment parameters that minimize a sum-over position for the region of interest.

Abstract: A method includes receiving head-tracking data that describe one or more positions of people while the people are viewing a three-dimensional video. The method further includes generating a probabilistic model of the one or more positions of the people based on the head-tracking data, wherein the probabilistic model identifies a probability of a viewer looking in a particular direction as a function of time. The method further includes generating video segments from the three-dimensional video. The method further includes, for each of the video segments: determining a directional encoding format that projects latitudes and longitudes of locations of a surface of a sphere onto locations on a plane, determining a cost function that identifies a region of interest on the plane based on the probabilistic model, and generating optimal segment parameters that minimize a sum-over position for the region of interest.

Abstract: A method includes receiving two-dimensional video streams from a plurality of cameras, the two-dimensional video streams including multiple angles of a sporting event. The method further includes determining boundaries of the sporting event from the two-dimensional video streams. The method further includes identifying a location of a sporting object during the sporting event. The method further includes identifying one or more players in the sporting event. The method further includes identifying poses of each of the one or more players during the sporting event. The method further includes generating a three-dimensional model of the sporting event based on the boundaries of the sporting event, the location of the sporting object during the sporting event, and the poses of each of the one or more players during the sporting event. The method further includes generating a simulation of the three-dimensional model.

Abstract: A digital magazine application executing on a client device presents a digital magazine to a user including content items retrieved from one or more sources based on information associated with the user. When presenting the digital magazine, a cover is presented including an image and one or more headlines describing one or more content items included in the digital magazine. The cover may be generated by clustering content items included in the digital magazine and ranking content items in various clusters based on their characteristics. Based on the rankings, information describing content items from various clusters is included on the cover. Alternatively, the cover includes information describing content items identified based on the order in which the content items are presented by the digital magazine.

Abstract: A method includes generating a three-dimensional (3D) virtual reality video by stitching together image frames of an environment captured by a camera array. The method further includes generating graphical data for displaying a virtual reality user interface that includes the 3D virtual reality video. The method further includes determining, based on movement of a peripheral device, that a user moves a hand to be located in front of the 3D virtual reality video in the user interface and grabs the 3D virtual reality video from a first location to inside an object. The method further includes displaying the object with a preview of the 3D virtual reality video inside the object.

Abstract: A method includes generating graphical data for displaying a virtual reality user interface that includes a three-dimensional (3D) virtual reality video that is illustrated as being inside a sphere. The method further includes determining, based on movement of a peripheral device, that a user selects the sphere in the virtual reality user interface and the user moves the sphere on a head of the user. The method further includes displaying the 3D virtual reality video in the sphere surrounding the head of the user such that the user views a 360 degree environment corresponding to the 3D virtual reality video.

Abstract: A method includes generating a set of three-dimensional (3D) virtual reality videos by stitching together image frames of one or more environments captured by a camera array. The method further includes generating graphical data for displaying a virtual reality user interface that includes (1) selectable icons that correspond to the set of 3D virtual reality videos and (2) an object. The method further includes receiving, from a peripheral device, a selection of the object by a user of the peripheral device in the virtual reality user interface and an indication of a desire to move the object to be positioned in front of a first 3D virtual reality video from the set of virtual reality videos. The method further includes providing a first 3D preview of the first 3D virtual reality video within the object.

Abstract: A method includes receiving head-tracking data that describe one or more positions of people while the people are viewing a three-dimensional video. The method further includes generating a probabilistic model of the one or more positions of the people based on the head-tracking data, wherein the probabilistic model identifies a probability of a viewer looking in a particular direction as a function of time. The method further includes generating video segments from the three-dimensional video. The method further includes, for each of the video segments: determining a directional encoding format that projects latitudes and longitudes of locations of a surface of a sphere onto locations on a plane, determining a cost function that identifies a region of interest on the plane based on the probabilistic model, and generating optimal segment parameters that minimize a sum-over position for the region of interest.

Abstract: A digital magazine application executing on a client device presents a digital magazine to a user including content items retrieved from one or more sources based on information associated with the user. When presenting the digital magazine, a cover is presented including an image and one or more headlines describing one or more content items included in the digital magazine. The cover may be generated by clustering content items included in the digital magazine and ranking content items in various clusters based on their characteristics. Based on the rankings, information describing content items from various clusters is included on the cover. Alternatively, the cover includes information describing content items identified based on the order in which the content items are presented by the digital magazine.

Abstract: A digital magazine server creates a section of a digital magazine including content items identified based on a search query received from a user. The digital magazine server receives a request to create the section that includes the search query and applies the search query to one or more sources. Content items satisfying the search query are retrieved from the one or more sources. A section of the digital magazine including various content items satisfying the search query is generated and presented to the user requesting creation of the section as well as additional users of the digital magazine server.