Abstract: A method for conducting a three dimensional (3D) video conference between multiple participants, the method may include determining, for each participant, updated 3D participant representation information within the virtual 3D video conference environment, that represents participants; wherein the determining comprises estimating 3D participant representation information of one or more hidden areas of a face of a participant that are hidden from the camera that captures at least one visible area of the face of the participant; and generating, for at least one participant, an updated representation of virtual 3D video conference environment, the updated representation of virtual 3D video conference environment represents the updated 3D participant representation information for at least some of the multiple participants.

Abstract: A method for conducting a three dimensional (3D) video conference between multiple participants, the method may include determining, for each participant, updated 3D participant representation information within the virtual 3D video conference environment, that represents participant; wherein the determining comprises compensating for difference between an actual optical axis of a camera that acquires images of the participant and a desired optical axis of a virtual camera; and generating, for at least one participant, an updated representation of virtual 3D video conference environment, the updated representation of virtual 3D video conference environment represents the updated 3D participant representation information for at least some of the multiple participants.

Abstract: A method for conducting a three dimensional (3D) video conference between multiple participants, the method may include determining, for each participant and multiple times during the 3D video conference, updated 3D participant representation information within the virtual 3D video conference environment; and generating, for at least one participant and multiple times during the 3D video conference, an updated representation of a virtual 3D video conference environment, the updated representation of virtual 3D video conference environment represents the updated 3D participant representation information for at least some of the multiple participants; and wherein the 3D participant representation information comprises a 3D model and one or more texture maps.

Abstract: A method for predicting behavior changes of a participant of a virtual three dimensional (3D) video conference, the method may include determining, for each part of multiple parts of the virtual 3D video conference, and by a first computerized unit, (a) a participant behavioral predictor to be applied by a second computerized unit during the part of the virtual 3D video conference, (b) one or more prediction inaccuracies related to the applying of the participant behavioral predictor during the part of the virtual 3D video conference, and (c) whether to generate and transmit to the second computerized unit prediction inaccuracy metadata that is indicative of at least one prediction inaccuracy that affects a representation of the participant within a virtual 3D video conference environment presented to another participant of the virtual 3D video conference during the part of the virtual 3D video conference; and generating and transmitting to the second computerized unit the prediction inaccuracy metadata, when

Abstract: A method for virtually mimicking an arm movement of participant of a three dimensional (3D) video conference, the method may include (i) obtaining joints movement information about joints movements of an arm of a participant of the 3D video conference, based on a movement of the arm of the participant that was captured by a video taken by a camera of the participant, wherein arm of the participant is free of physical joint movement markers; (ii) generating, an arm skeletal model that represents the joins movement of the arm, based on the joints movement information; (iii) generating, by a machine learning process, a renderable 3D model of the arm that mimics the movement of the arm of the participant; and (iv) responding to the generating of the renderable 3D model, wherein the responding comprises at least one out of (a) rendering an avatar of the participant based on the renderable 3D model, (b) storing renderable 3D model information, or (c) sending the renderable 3D model information to another computeriz

Abstract: A method for conducting a three dimensional (3D) video conference with multiple participants, the method may include (i) receiving, from a first participant and by software used to conduct the 3D video conference call, a request to see a second avatar that represents a second participant, within a representation of a virtual 3D environment displayed to the first participant during the 3D video conference; (ii) displaying the second avatar within the representation following a reception of (a) a first approval from the software to display the avatar within the representation, and (b) a second participant approval to display the avatar within the representation; and (iii) avoiding from displaying the second avatar within the representation until receiving the first approval and the second participant approval.

Abstract: A method for three dimensional modeling and rendering of head hair, the method may include obtaining a three dimensional (3D) point cloud of head hair points of a person; determining head hair points related 3D directions indicative of 3D directions of candidate strands that pass through the head hair points; grouping the hear hair points into multiple strand groups, wherein the grouping is based on distances between the head hair points and the head hair points 3D directions; wherein each strand group is associated with strand spatial information; and generating, by a machine learning process, a representation of the head hair based on strand spatial information of the multiple strand groups and on strand shape information.

Abstract: A method for avatar virtual arm movement, the method may include (i) capturing, by a camera of a participant of a video conference, a hand gesture made by the participant without capturing an arm movement of the participant, the arm movement is associated with the hand gesture; (ii) determining the arm movement of the participant, based on the hand gesture; (iii) determining a virtual movement of an arm of an avatar of the participant within a virtual video conference environment, the virtual movement of the arm of the avatar of the participant mimics the arm movement of the participant; and (iv) assisting to perform the virtual arm movement of the avatar within the virtual video conference environment.

Abstract: A method for conducting a virtual three dimensional (3D) video conference between multiple participants, the method may include receiving by a user device of a first participant of the virtual 3D video conference, reference second participant 3D representation information for generating a second participant 3D representation under different constraints. The different constraints include at least one out of (a) a touch up constraint, (b) a makeup constraint, and (c) one or more circumstances constraint.

Abstract: A method for performing virtual non-verbal communication cues within a virtual environment of a video conference, the method may include: (i) sensing that a certain participant of a video conference performs non-verbal communication cues in relation to virtual items that appear in a version of a virtual video conference environment that is displayed on a display of the certain participant; (ii) determining, by a machine learning process, virtual non-verbal communication cues to be executed by a certain avatar that represents the certain participant, wherein the virtual non-verbal communication cues mimic the non-verbal communication cues performed by the certain participant; and (iii) assisting to perform the virtual non-verbal communication cues of the certain avatar within the virtual video conference environment.

Abstract: A method for virtual 3D video conference environment generation, the method may include (a) determining a first optical axis of a first virtual camera, the first optical axis represents a line of sight of the participant while a participant of the 3D video conference environment looks at a current displayed version of a virtual 3D video conference environment (V3DVCE); the current displayed version of the V3DVCE is displayed on a display; (b) determining a second optical axis of a second virtual camera that virtually captures the V3DVCE to provide the current displayed version of the V3DVCE; and (c) generating a next displayed version of the V3DVCE based on at least one of the first optical axis and the second optical axis.

Abstract: A method for virtually mimicking an arm movement of participant of a 3D video conference, the method may include (i) obtaining a video that captures an arm movement of a participant of the 3D video conference; (ii) generating, based on the video, joint movement information about joints movements that facilitated the arm movement; (iii) receiving, by a machine learning process, the joint movement information; (iv) determining, by the machine learning process, arm appearance information indicative of an appearance of the arm of the participant during the arm movement; wherein the determining is based on a machine learning process based mapping between joint movements and texture and muscle movements; and (v) responding to the determining, wherein the responding comprises at least one out of (a) rendering an avatar of the participant based on the arm appearance information, (b) storing the arm appearance information, or (c) sending the arm appearance information to another computerized device related to the 3D v

Abstract: A method for conducting a three dimensional (3D) video conference between multiple participants, the method may include receiving second participant metadata and first viewpoint metadata by a first unit that is associated with a first participant, wherein the second participant metadata is indicative of a pose of a second participant and an expression of the second participant, wherein the first viewpoint metadata is indicative of a virtual position from which the first participant requests to view an avatar of the second participant; generating, by the first unit, and based on the second participant metadata and the first viewpoint metadata, a second participant representation information; wherein the second participant representation information comprises a compact 3D model of the second participant and a second participant texture map; and determining, for the first participant and during the 3D video conference, a representation of virtual 3D video conference environment, wherein the determining is based

Abstract: A method for generating a texture map used during a video conference, the method may include obtaining multiple texture maps of multiple areas of at least a portion of a three-dimensional (3D) object; wherein the multiple texture maps comprise a first texture map of a first area and of a first resolution, and a second texture map of a second area and of a second resolution, wherein the first area differs from the first area and the first resolution differs from the second resolution; and generating a texture map of the at least portion of the 3D object, the generating is based on the multiple texture maps; and utilizing the visual representation of the at least portion of the 3D object based on the texture map of the at least portion of the 3D object during the video conference.

Abstract: A method for generating alpha channel information related to a person, the method may include generating the alpha channel information related to the person by an alpha channel neural network; wherein the alpha channel machine learning process is trained using ground truth alpha channel information that is associated with background information; wherein the ground-truth alpha channel information is generated by: obtaining input images of the person; wherein each image comprises the person and an arbitrary background; repeating, for each input image of the input images, converting the input image, by a portrait matting predictor, to (a) a first colored background image that comprises the person and a background of a first color, and (b) a second colored background image that comprises the person and a background of a second color; wherein the first color differs from the second color.

Abstract: A method for video conference environment generation, the method may include detecting a participant gaze pattern in relation to a display that displays a version of a virtual three dimensional virtual 3D video conference environment video conference environment (V3DVCE); and changing, without an explicit request from the participant, one or more display parameters of the V3DVCE to induce a change of at least one participant gaze pattern parameter

Abstract: A method for generating an avatar of a participant of a three dimensional (3D) video conference, the method may include acquiring visual information, by a camera of a participant; generating an avatar of the participant as seen from a point of view of a virtual camera that is virtually located at a physical location of the camera; comparing between the avatar and the visual information to provide a comparison result; and amending the avatar or at least one building block of the avatar to compensate for one or more differences between the avatar and the visual information when the comparison results is indicative of the one or more differences.

Abstract: A method for foreground and background segmentation related to a virtual three-dimensional (3D) video conference, the method may include segmenting each image of multiple images of a video stream, to segments, each segment has one or more properties that are constant; determining temporal properties of the segments; and classifying each segment as a background segment or a foreground segment, based at least in part, on the temporal properties of the segments.

Abstract: A method for conducting a three dimensional (3D) video conference between multiple participants, the method may include acquiring visual information, by a visual sensing unit related to a certain participant; identifying multiple persons that appear in the visual information; finding, out of the multiple persons, at least one relevant person; determining 3D entity representation information, for each of the at least one relevant person; and generating, for at least one participant, a representation of a virtual 3D video conference environment, based on the 3D entity representation information for each of the at least one relevant person.

Abstract: A method for audio quality improvement related to a participant of a virtual three dimensional (3D) video conference, the method may include: determining participant generated audio, by a machine learning process and based on image analysis of a video of the participant obtained during the virtual 3D video conference; and generating participant related audio information based at least on the participant generated audio; wherein the participant related audio information, once provided to a computerized system of another participant, causes the computerized system of the other participant to generate participant related audio of higher quality than participant audio when the participant audio is included in sensed audio that is sensed by an audio sensor that is associated with the participant.