Apparatus, systems and methods for generating 3D model data from a media content event
First Claim
1. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
- receiving, at a media device, a user request that is associated with an interest by a user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event;
accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received;
identifying at least one image of a candidate physical object that is shown in the accessed first video image frame;
generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object;
receiving a user response that is associated with the candidate physical object,wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, orwherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in;
defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in;
accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event;
identifying the physical object of interest in the plurality of second video image frames;
generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and
generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames,wherein identifying the at least one image of the candidate physical object that is shown in the accessed first video image frame comprises;
communicating the first video image frame from the media device to a remote 3D model site, wherein the at least one image of the candidate physical object that is shown in the accessed first video image frame is identified at the remote 3D model site; and
receiving at least the image of the at least one candidate physical object from the remote 3D model site,wherein the user confirmation image is generated at the media device based on the received image of the at least one candidate physical object.
4 Assignments
0 Petitions
Accused Products
Abstract
Three dimension (3D) model generation systems and methods are operable to generate 3D model data corresponding to images of a physical object of interest that are viewed in a presenting media content event. An exemplary embodiment receives a user request that is associated with an interest by the user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event. A plurality of video image frames are selected from the scene. Then, 3D model data of the physical object of interest is generated based on at least the selected video image frames of the scene.
18 Citations
16 Claims
-
1. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
-
receiving, at a media device, a user request that is associated with an interest by a user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event; accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object; receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames, wherein identifying the at least one image of the candidate physical object that is shown in the accessed first video image frame comprises; communicating the first video image frame from the media device to a remote 3D model site, wherein the at least one image of the candidate physical object that is shown in the accessed first video image frame is identified at the remote 3D model site; and receiving at least the image of the at least one candidate physical object from the remote 3D model site, wherein the user confirmation image is generated at the media device based on the received image of the at least one candidate physical object.
-
-
2. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
-
receiving, at a media device, a user request that is associated with an interest by a user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event; accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object; receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames, wherein identifying the at least one image of the candidate physical object that is shown in the accessed first video image frame comprises; communicating the first video image frame from the media device to a remote 3D model site, wherein the at least one image of the candidate physical object that is shown in the accessed first video image frame is identified at the remote 3D model site; and receiving the user confirmation image that has the at least one image of the candidate physical object from the remote 3D model site.
-
-
3. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
-
receiving, at a media device, a user request that is associated with an interest by a user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event; accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object; receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames; generating an image based on the generated 3D model data, wherein the generated 3D model image corresponds to the physical object of interest; and receiving a confirmation response from the user, wherein the confirmation response indicates that the generated 3D model data is acceptable to the user for printing a 3D printable object using a 3D printer, or wherein the confirmation response indicates that the generated 3D model data is not acceptable to the user for printing the 3D printable object using the 3D printer. - View Dependent Claims (4, 5, 6)
-
-
7. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
-
receiving at a media device, a user request that is associated with an interest by a user to obtain a
31) model of a physical object of interest that is being shown in a scene of a currently presenting media content event;accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user;
wherein the user confirmation image includes the at least one image of the candidate physical object;receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames, wherein the media content event being presented to the user is a first media content event, the method further comprising; accessing a second media content event from a memory medium in response to receiving the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, wherein the second media content event is the same as the first media content event, and wherein the plurality of second video image frames are obtained from the accessed second media content event.
-
-
8. A method that generates three dimensional (3D)) models based on images in a media content event, the method comprising:
-
receiving, at a media device, a user request that is associated with an interest by a user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event; accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object; pausing presentation of the media content event while the user confirmation image is presented to the user, wherein presentation of the user confirmation image concludes and presentation of the media content event resumes after the user response is received; receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames.
-
-
9. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
-
receiving, at a media device, a user request that is associated with an interest by a user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event; accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object; presenting the user confirmation image concurrently with a continuing presentation of the media content event, wherein presentation of the user confirmation image concludes after the user response is received; receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames.
-
-
10. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
-
receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames, wherein the generating 3D model data is generated based on a passive modeling technique that determines depth attributes of various portions of the physical object of interest from the plurality of second video image frames, wherein the plurality of second video image frames of the scene were filmed using an uncalibrated camera, wherein the plurality of second video image frames of the scene were filmed without a controlled light source that projects a reference line onto the physical object of interest, and wherein the plurality of second video image frames of the scene were filmed without a known camera location in 3D space of the uncalibrated camera with respect to the physical object of interest.
-
-
11. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
-
receiving, at a media device, a user request that is associated with an interest by a user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event; accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object; receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames, wherein the scene comprises a plurality of first scene portions filmed by a first camera and a plurality of second scene portions filmed by a second camera, wherein the plurality of first scene portions filmed by the first camera include images of the physical object of interest, and wherein the plurality of second scene portions filmed by the second camera do not include images of the physical object of interest, the method further comprising; identifying the plurality of first scene portions filmed by the first camera, wherein the plurality of second video image frames are accessed from the identified plurality of first scene portions filmed by the first camera.
-
-
12. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
-
receiving, at a media device, a user request that is associated with an interest by a user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event; accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object; receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames, wherein the scene is a first scene, and wherein the media content event is a first media content event, the method further comprising; identifying at least one second scene in the first media content event or in a second media content event that is different from the first media content event, wherein the second scene includes images of the physical object of interest; accessing a plurality of third video image frames from the second scene; identifying the physical object of interest in the plurality of third video image frames obtained from the second scene; generating the image of the physical object of interest from each one of the plurality of third video image frames obtained from a third scene; defining a plurality of first vertices for the physical object of interest identified in the plurality of second video image frames obtained from the first scene, wherein each vertex uniquely corresponds to point locations on the physical object of interest; defining a plurality of second vertices for the physical object of interest identified in the plurality of third video image frames obtained from the second scene wherein each vertex uniquely corresponds to point locations on the physical object of interest; selecting a first vertex from the plurality of first vertices and a second vertex from the plurality of second vertices, wherein the first vertex and the second vertex each correspond to a first point location on the physical object of interest; selecting a third vertex from the plurality of first vertices and a fourth vertex from the plurality of second vertices, wherein the third vertex and the fourth vertex each correspond to a second point location on the physical object of interest; determining a first relationship between the first vertex and the third vertex; determining a second relationship between the second vertex and the fourth vertex; determining a difference between the first relationship and the second relationship; and compensating the images of the physical object of interest obtained from each one of the plurality of third video image frames based on the determined difference between the first relationship and the second relationship, wherein the 3D model data is generated based on at least the images of the physical object of interest that are generated from the plurality of second video image frames obtained from the first scene and the plurality of third compensated video image frames obtained from second scene.
-
-
13. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
-
receiving at a media device, a user request that is associated with an interest by a user to obtain a
31) model of a physical object of interest that is being shown in a scene of a currently presenting media content event;accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object; receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames, wherein the plurality of second video image frames of the scene are separated from each other by a first sampling duration, the method further comprising; defining a first vertex for the physical object of interest identified in a first one of the plurality of second video image frames obtained from the first scene, wherein the first vertex uniquely corresponds to a point on the physical object of interest; defining a second vertex for the physical object of interest identified a second one of the plurality of second video image frames obtained from the first scene, wherein the second vertex uniquely corresponds to the point on the physical object of interest; determining a difference between a location of the first vertex and the third vertex; comparing the determined difference with a difference threshold; wherein when the determined difference exceeds the threshold, using the plurality of second video image frames of the scene to generate the 3D model data; and wherein when the determined difference is less than the difference threshold, the method further comprises; increasing the first sampling duration to a second sampling duration; and selecting a plurality of third video image frames of the scene, wherein the plurality of third video image frames of the scene are separated from each other by the increased second sampling duration.
-
-
14. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising,
receiving, at a media device, a user request that is associated with an interest by a user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event; -
accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object; receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames the method further comprising; determining whether there is a hidden side of the physical object of interest that is not visible in any of the plurality of second video image frames; defining a plane that bisects the physical object of interest into a first mirror image half that is visible in the plurality of second video image frames and a second mirror half that includes at least the hidden side of the physical object of interest; defining a plurality of first vertices for the first mirror image half based on the plurality of second video image frames, wherein each of the plurality of first vertices uniquely correspond to a point location of a visible side of the physical object of interest; and estimating a plurality of second vertices for the hidden side of the physical object of interest based on corresponding ones of the plurality of first vertices, wherein each of the second vertices are at a same projection location on the defined plane as a projection location of the corresponding visible like first vertex, wherein each of the second vertices are at a distance out from the defined plane as a distance out from the defined plane of the corresponding visible first vertex, and wherein the 3D model data is generated based on the plurality of first vertices and the plurality of second vertices.
-
-
15. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
-
receiving, at a media device, a user request that is associated with an interest by a user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event; accessing, at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object; receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames, wherein the physical object of interest is a first physical object of interest, the method further comprising; determining whether there is a hidden side of the physical object of interest that is not visible in any of the plurality of second video image frames; determining an identity of the physical object of interest; defining a plurality of first vertices based on the plurality of second video image frames, wherein each of the plurality of first vertices uniquely correspond to a point location of a visible side of the physical object of interest; accessing at least one image of a second physical object of interest from a memory medium, wherein the second physical object of interest has a same identity as the first physical object of interest, and wherein the image of the second physical object of interest includes an image of the hidden side of the first physical object of interest; and estimating a plurality of second vertices for the hidden side of the physical object of interest based on the accessed image of the second physical object of interest, wherein the 3D model data is generated based on the plurality of first vertices and the plurality of second vertices.
-
-
16. A method that generates three dimensional (3D) models based on images in a media content event, the method comprising:
-
receiving, at a media device, a user request that is associated with an interest by a user to obtain a 3D model of a physical object of interest that is being shown in a scene of a currently presenting media content event; accessing at the media device, a first video image frame of the scene of the media content event, wherein the first video image frame corresponds to a video image being presented in the scene of the media content event at a time that the user request is received; identifying at least one image of a candidate physical object that is shown in the accessed first video image frame; generating a user confirmation image that is presentable to the user, wherein the user confirmation image includes the at least one image of the candidate physical object; receiving a user response that is associated with the candidate physical object, wherein the user response indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in, or wherein the user response indicates that the candidate physical object does not correspond to the physical object of interest that the user is interested in; defining the candidate physical object as the physical object of interest when the user response that indicates that the candidate physical object corresponds to the physical object of interest that the user is interested in; accessing a plurality of second video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the scene of a video portion of the currently presenting media content event; identifying the physical object of interest in the plurality of second video image frames; generating an image of the physical object of interest from each one of the plurality of second video image frames when the physical object of interest is identified in the plurality of second video image frames; and generating 3D model data based on at least the images of the physical object of interest that are generated from the plurality of second video image frames, wherein the scene is a first scene, the method further comprising; determining whether there is a hidden side of the physical object of interest that is not visible in any of the plurality of second video image frames; identifying a second scene in the media content event that shows at least the hidden side of the physical object of interest; defining a plurality of first vertices based on the plurality of second video image frames, wherein each of the plurality of first vertices uniquely correspond to a point location of a visible side of the physical object of interest; accessing a plurality of third video image frames, wherein the plurality of second video image frames comprises a plurality of video frames from the second scene of the media content event; identifying at least the hidden side of the physical object of interest in the plurality of third video image frames; generating an image of at least the hidden side of the object of interest from each one of the plurality of third video image frames; and defining a plurality of second vertices for at least the hidden side of the physical object of interest based on the plurality of third video image frames, wherein the 3D model data is generated based on the plurality of first vertices and the plurality of second vertices.
-
Specification