Systems and methods for providing personal video services
First Claim
1. A method of video conferencing, the method comprising the steps of:
- detecting a human face of a video conference participant depicted in portions of a video stream;
creating by explicitly modeling one or more explicit object models to model the face of the video conference participant;
generating one or more implicit object models relative to parameters obtained from the explicit object models to facilitate creation of a compact encoding of the video conference participant'"'"'s face;
using the implicit object model, creating a photorealistic avatar representation of the video conference participant;
periodically checking to determine whether the implicit object model is working optimally; and
responding to a determination that the implicit object model is not working by processing the step of detecting a human face of a video conference participant and in response to detecting a human face, searching for existing calibration information for the detected human face.
1 Assignment
0 Petitions
Accused Products
Abstract
Systems and methods for processing video are provided. Video compression schemes are provided to reduce the number of bits required to store and transmit digital media in video conferencing or videoblogging applications. A photorealistic avatar representation of a video conference participant is created. The avatar representation can be based on portions of a video stream that depict the conference participant. A face detector is used to identify, track and classify the face. Object models including density, structure, deformation, appearance and illumination models are created based on the detected face. An object based video compression algorithm, which uses machine learning face detection techniques, creates the photorealistic avatar representation from parameters derived from the density, structure, deformation, appearance and illumination models.
-
Citations
31 Claims
-
1. A method of video conferencing, the method comprising the steps of:
-
detecting a human face of a video conference participant depicted in portions of a video stream; creating by explicitly modeling one or more explicit object models to model the face of the video conference participant; generating one or more implicit object models relative to parameters obtained from the explicit object models to facilitate creation of a compact encoding of the video conference participant'"'"'s face; using the implicit object model, creating a photorealistic avatar representation of the video conference participant; periodically checking to determine whether the implicit object model is working optimally; and responding to a determination that the implicit object model is not working by processing the step of detecting a human face of a video conference participant and in response to detecting a human face, searching for existing calibration information for the detected human face. - View Dependent Claims (2, 3, 4, 5, 6, 8, 9, 10, 12, 13, 14, 15, 16, 17, 18)
-
-
7. A video conferencing system comprising:
-
a face detector configured to detect a face of a video conference participant in a video stream; a calibrator configured to generate a calibration model calibrating the face of the video conference participant; an explicit object modeler configured to generate one or more explicit object models, in combination with the calibrator and face detector, the explicit object models modeling portions of the video stream depicting the face of the video conference participant based on the calibration model; an implicit object modeler configured to build one or more implicit object models relative to parameters from the explicit object models to facilitate creation of a compact encoding of the participant'"'"'s face; the system operable to generate a photorealistic avatar representation of the video conference participant from the implicit object model; the system operable to periodically check to determine whether the implicit object model is working optimally; and the system operable to respond to a determination that the implicit object model is not working by using the face detector to detect a face of a video conference participant and responding to the face detector detecting a face by searching for an existing calibration model for the detected face.
-
-
11. A method of video conferencing, the method comprising the steps of:
-
detecting a human face of a video conference participant depicted in portions of a video stream; creating by explicitly modeling one or more explicit object models to model the face of the video conference participant; generating one or more implicit object models relative to parameters obtained from the explicit object models to facilitate creation of a compact encoding of the video conference participant'"'"'s face; using the implicit object model, creating a photorealistic avatar representation of the video conference participant; periodically checking to determine whether the implicit object model is working optimally, where the determination that the implicit object modeling is working optimally causes subsequent instances of the photorealistic avatar representation of the conference participant to be created without relying on the step of detecting a human face in the portions of the video stream. - View Dependent Claims (20)
-
-
19. A method of video conferencing, the method comprising the steps of:
-
generating explicit object models to model a human face of a video conference participant depicted in portions of a video stream; using parameters from the explicit object models, generating one or more implicit object models to create a photorealistic avatar representation of the video conference participant, where the explicit object model parameters are used to define expectations for the implicit object model regarding how lighting interacts with a structure of the face of the video conference participant; periodically checking to determine whether the implicit object model is working optimally; and responding to a determination that the implicit object model is not working by detecting a face of a video conference participant and responding to the detection by searching for existing calibration information for the detected face.
-
-
21. A video conferencing system comprising:
-
a face detector configured to detect a face of a video conference participant in a video stream; a calibrator configured to generate a calibration model calibrating the face of the video conference participant; an explicit object modeler configured to generate one or more explicit object models, in combination with the calibrator and face detector, the explicit object models modeling portions of the video stream depicting the face of the video conference participant based on the calibration model; an implicit object modeler configured to build one or more implicit object models relative to parameters from the explicit object models to facilitate creation of a compact encoding of the participant'"'"'s face; the system operable to generate a photorealistic avatar representation of the video conference participant from the implicit object model; and the system operable to periodically check to determine whether the implicit object model is working optimally, where the determination that the implicit object modeling is working optimally causes subsequent instances of the photorealistic avatar representation of the conference participant to be created without relying on the step of detecting a human face in the portions of the video stream.
-
-
22. A method of video conferencing, the method comprising the steps of:
-
detecting a human face of a video conference participant depicted in portions of a video stream; creating by explicitly modeling one or more explicit object models to model the face of the video conference participant; generating one or more implicit object models relative to parameters obtained from the explicit object models to facilitate creation of a compact encoding of the video conference participant'"'"'s face; using the implicit object model, creating a photorealistic avatar representation of the video conference participant; and periodically checking to determine whether the implicit object modeling is working optimally including determining that the implicit object models, which are used to create the photorealistic avatar representation, are working optimally by; determining that reprojection error is low in the photorealistic avatar representation; and determining that there is a significant amount of motion in the photorealistic avatar representation.
-
-
23. A video conferencing system comprising:
-
a face detector configured to detect a face of a video conference participant in a video stream; a calibrator configured to generate a calibration model calibrating the face of the video conference participant; an explicit object modeler configured to generate one or more explicit object models, in combination with the calibrator and face detector, the explicit object models modeling portions of the video stream depicting the face of the video conference participant based on the calibration model; an implicit object modeler configured to build one or more implicit object models relative to parameters from the explicit object models to facilitate creation of a compact encoding of the participant'"'"'s face; the system operable to generate a photorealistic avatar representation of the video conference participant from the implicit object model; and the system operable to periodically check to determine whether the implicit object modeling is working optimally such that the system is operable to determine that the implicit object models, which are used to create the photorealistic avatar representation, are working optimally by; determining that reprojection error is low in the photorealistic avatar representation; and determining that there is a significant amount of motion in the photorealistic avatar representation.
-
-
24. A method of video conferencing, the method comprising the steps of:
-
detecting a human face of a video conference participant depicted in portions of a video stream; creating by explicitly modeling one or more explicit object models to model the face of the video conference participant; generating one or more implicit object models relative to parameters obtained from the explicit object models to facilitate creation of a compact encoding of the video conference participant'"'"'s face; using the implicit object model, creating a photorealistic avatar representation of the video conference participant; and periodically checking to determine whether the implicit object modeling is working optimally including determining that the implicit object model is not working optimally by; determining that processing of the photorealistic avatar representation uses a disproportional amount of transmission bandwidth;
ordetermining that the implicit object modeling is not working optimally if reprojection error is high.
-
-
25. A video conferencing system comprising:
-
a face detector configured to detect a face of a video conference participant in a video stream; a calibrator configured to generate a calibration model calibrating the face of the video conference participant; an explicit object modeler configured to generate one or more explicit object models, in combination with the calibrator and face detector, the explicit object models modeling portions of the video stream depicting the face of the video conference participant based on the calibration model; an implicit object modeler configured to build one or more implicit object models relative to parameters from the explicit object models to facilitate creation of a compact encoding of the participant'"'"'s face; the system operable to generate a photorealistic avatar representation of the video conference participant from the implicit object model; and the system operable to periodically check to determine whether the implicit object modeling is working optimally including determining that the implicit object model is not working optimally by; determining that processing of the photorealistic avatar representation uses a disproportional amount of transmission bandwidth;
or determining that the implicit object modeling is not working optimally if reprojection error is high.
-
-
26. A method of video conferencing, the method comprising the steps of:
-
detecting a human face of a video conference participant depicted in portions of a video stream; creating by explicitly modeling one or more explicit object models to model the face of the video conference participant; generating one or more implicit object models relative to parameters obtained from the explicit object models to facilitate creation of a compact encoding of the video conference participant'"'"'s face; and using the implicit object model, creating a photorealistic avatar representation of the video conference participant; wherein creating a photorealistic avatar representation of the video conference participant includes enabling the video conference participant to adjust a gaze of their respective photorealistic avatar representation.
-
-
27. A video conferencing system comprising:
-
a face detector configured to detect a face of a video conference participant in a video stream; a calibrator configured to generate a calibration model calibrating the face of the video conference participant; an explicit object modeler configured to generate one or more explicit object models, in combination with the calibrator and face detector, the explicit object models modeling portions of the video stream depicting the face of the video conference participant based on the calibration model; an implicit object modeler configured to build one or more implicit object models relative to parameters from the explicit object models to facilitate creation of a compact encoding of the participant'"'"'s face; and the system operable to generate a photorealistic avatar representation of the video conference participant from the implicit object model; wherein creating a photorealistic avatar representation of the video conference participant includes enabling the video conference participant to adjust a gaze of their respective photorealistic avatar representation.
-
-
28. A method of video conferencing, the method comprising the steps of:
-
detecting a human face of a video conference participant depicted in portions of a video stream; creating by explicitly modeling one or more explicit object models to model the face of the video conference participant; generating one or more implicit object models relative to parameters obtained from the explicit object models to facilitate creation of a compact encoding of the video conference participant'"'"'s face; and using the implicit object model, creating a photorealistic avatar representation of the video conference participant; wherein the implicit object models are configured using parameters obtained from the explicit object models, such that the explicit object model parameters are used as a ground truth for estimating portions of the video stream with the implicit object models; wherein the explicit object model parameters are used to define expectations about how lighting interacts with the structure of the face of the video conference participant.
-
-
29. A video conferencing system comprising:
-
a face detector configured to detect a face of a video conference participant in a video stream; a calibrator configured to generate a calibration model calibrating the face of the video conference participant; an explicit object modeler configured to generate one or more explicit object models, in combination with the calibrator and face detector, the explicit object models modeling portions of the video stream depicting the face of the video conference participant based on the calibration model; an implicit object modeler configured to build one or more implicit object models relative to parameters from the explicit object models to facilitate creation of a compact encoding of the participant'"'"'s face; and the system operable to generate a photorealistic avatar representation of the video conference participant from the implicit object model; wherein the implicit object model is configured using parameters obtained from the explicit object models, such that the explicit object model parameters are used as a ground truth for estimating portions of the video stream with the implicit object model; wherein the explicit object model parameters are used to define expectations about how lighting interacts with the structure of the face of the video conference participant.
-
-
30. A method of video conferencing, the method comprising the steps of:
-
detecting a human face of a video conference participant depicted in portions of a video stream; creating by explicitly modeling one or more explicit object models to model the face of the video conference participant; generating one or more implicit object models relative to parameters obtained from the explicit object models to facilitate creation of a compact encoding of the video conference participant'"'"'s face; and using the implicit object model, creating a photorealistic avatar representation of the video conference participant; wherein the step of detecting a face includes using a Viola/Jones face detector which is operable to; identify corresponding elements of at least one object associated with the face in two or more video frames from the video stream; and track and classify the corresponding elements to identify relationships between the corresponding elements based on previously calibrated and modeled faces.
-
-
31. A video conferencing system comprising:
-
a face detector configured to detect a face of a video conference participant in a video stream; a calibrator configured to generate a calibration model calibrating the face of the video conference participant; an explicit object modeler configured to generate one or more explicit object models, in combination with the calibrator and face detector, the explicit object models modeling portions of the video stream depicting the face of the video conference participant based on the calibration model; an implicit object modeler configured to build one or more implicit object models relative to parameters from the explicit object models to facilitate creation of a compact encoding of the participant'"'"'s face; and the system operable to generate a photorealistic avatar representation of the video conference participant from the implicit object model; wherein the implicit object model provides an implicit representation of the face of the video conference participant; wherein the face detector is configured to use a Viola/Jones face detector which is operable to; identify corresponding elements of at least one object associated with the face in two or more video frames from the video stream; and track and classify the corresponding elements to identify relationships between the corresponding elements based on previously calibrated and modeled faces.
-
Specification