Abstract: Implementations described herein relate to methods, systems, and computer-readable media to render a foreground video. In some implementations, a method includes receiving a plurality of video frames that include depth data and color data. The method further includes downsampling the frames of the video. The method further includes, for each frame, generating an initial segmentation mask that categorizes each pixel of the frame as foreground pixel or background pixel. The method further includes determining a trimap that classifies each pixel of the frame as known background, known foreground, or unknown. The method further includes, for each pixel that is classified as unknown, calculating and storing a weight in a weight map. The method further includes performing fine segmentation to obtain a binary mask for each frame. The method further includes upsampling the plurality of frames based on the binary mask for each frame to obtain a foreground video.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to render a foreground video. In some implementations, a method includes receiving a plurality of video frames that include depth data and color data. The method further includes downsampling the frames of the video. The method further includes, for each frame, generating an initial segmentation mask that categorizes each pixel of the frame as foreground pixel or background pixel. The method further includes determining a trimap that classifies each pixel of the frame as known background, known foreground, or unknown. The method further includes, for each pixel that is classified as unknown, calculating and storing a weight in a weight map. The method further includes performing fine segmentation to obtain a binary mask for each frame. The method further includes upsampling the plurality of frames based on the binary mask for each frame to obtain a foreground video.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to render a foreground video. In some implementations, a method includes receiving a plurality of video frames that include depth data and color data. The method further includes downsampling the frames of the video. The method further includes, for each frame, generating an initial segmentation mask that categorizes each pixel of the frame as foreground pixel or background pixel. The method further includes determining a trimap that classifies each pixel of the frame as known background, known foreground, or unknown. The method further includes, for each pixel that is classified as unknown, calculating and storing a weight in a weight map. The method further includes performing fine segmentation to obtain a binary mask for each frame. The method further includes upsampling the plurality of frames based on the binary mask for each frame to obtain a foreground video.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to render a foreground video. In some implementations, a method includes receiving a plurality of video frames that include depth data and color data. The method further includes downsampling the frames of the video. The method further includes, for each frame, generating an initial segmentation mask that categorizes each pixel of the frame as foreground pixel or background pixel. The method further includes determining a trimap that classifies each pixel of the frame as known background, known foreground, or unknown. The method further includes, for each pixel that is classified as unknown, calculating and storing a weight in a weight map. The method further includes performing fine segmentation to obtain a binary mask for each frame. The method further includes upsampling the plurality of frames based on the binary mask for each frame to obtain a foreground video.

Abstract: Methods and systems are provided for reusing audio streams in an audio mixing environment such that processing resources (e.g., CPU cycles) are not wasted on encoding the same audio streams multiple times (e.g., more than once). Instead, processing resources are conserved without comprising audio quality. The methods described herein are particularly useful when a participant transitions from using a shared encoder to using the participant's own encoder, and when the participant transitions from using the participant's own encoder to using a shared encoder.

Abstract: Methods and systems are provided for reusing audio streams in an audio mixing environment such that processing resources are not wasted on encoding the same audio streams multiple times. Instead, processing resources are conserved without comprising audio quality. The methods described herein are particularly useful when a participant transitions from using a shared encoder to using the participant's own encoder, and when the participant transitions from using the participant's own encoder to using a shared encoder.

Abstract: Methods and systems are provided for reusing audio streams in an audio mixing environment such that processing resources (e.g., CPU cycles) are not wasted on encoding the same audio streams multiple times (e.g., more than once). Instead, processing resources are conserved without comprising audio quality. The methods described herein are particularly useful when a participant transitions from using a shared encoder to using the participant's own encoder, and when the participant transitions from using the participant's own encoder to using a shared encoder.

Abstract: A method and an apparatus for indicating presence of a transient noise in a call are provided. The method comprises the steps of determining activity at an endpoint of the call by monitoring presence of a signal input from the endpoint into the call and monitoring presence of a potential source of transient noise at the endpoint. Further, based on the activity determination and the monitoring of the presence of a potential source of transient noise, a signal representative of the presence of a transient noise in the call is sent. The present invention is advantageous in that it enables improvement of the quality of the call.

Abstract: A control system for varying an audio level in a communication system, the control system comprising a receiving unit for receiving an audio signal and a video signal, a determining unit for determining a number of individuals speaking determined by performing recognition on either the audio signal or the video signal; and a gain adjustment unit for adjusting a gain of the audio signal based on said number of determined individuals that are speaking.

Abstract: The invention relates to a method and an apparatus for mixing audio signals. The invention is based on the idea to base selection of what audio channels to mix on the dynamic behavior of the audio channels in terms of whether they are active or not, rather than basing the selection on quantative measures of the audio channels. According to the invention, a set of audio channels are arranged in a mixing stack and a mixed audio signal is produced from the topmost channels above a predetermined threshold level in the stack. Whenever a channel becomes active, it is placed at the top of the stack.

Abstract: A method and an apparatus for indicating presence of a transient noise in a call are provided. The method comprises the steps of determining activity at an endpoint of the call by monitoring presence of a signal input from the endpoint into the call and monitoring presence of a potential source of transient noise at the endpoint. Further, based on the activity determination and the monitoring of the presence of a potential source of transient noise, a signal representative of the presence of a transient noise in the call is sent. The present invention is advantageous in that it enables improvement of the quality of the call.

Abstract: According to the invention, a method for processing an audio media stream that originates from a packet communication network is disclosed. In one step, packets are received as they arrive from the packet communication network. The packets are part of the audio media stream. A playout buffer in a media playout device is monitored. It is determined that the playout buffer is filled below a threshold. A portion of the audio media stream is retrieved when the playout buffer is filled below the threshold. The portion is stored in the playout buffer of the media playout device.

Abstract: The invention relates to a method and an apparatus for mixing audio signals. The invention is based on the idea to base selection of what audio channels to mix on the dynamic behaviour of the audio channels in terms of whether they are active or not, rather than basing the selection on quantative measures of the audio channels. According to the invention, a set of audio channels are arranged in a mixing stack and a mixed audio signal is produced from the topmost channels above a predetermined threshold level in the stack. Whenever a channel becomes active, it is placed at the top of the stack.

Abstract: According to the invention, a method for processing an audio media stream that originates from a packet communication network is disclosed. In one step, packets are received as they arrive from the packet communication network. The packets are part of the audio media stream. A playout buffer in a media playout device is monitored. It is determined that the playout buffer is filled below a threshold. A portion of the audio media stream is retrieved when the playout buffer is filled below the threshold. The portion is stored in the playout buffer of the media playout device.