Abstract: Techniques presented herein provide an improved relay user experience and improved management of scarce computing and network resources as the number of relay endpoints increases. A sourcing endpoint device may generate a media feed, such as video and/or audio feed, representing contribution from a conference participant. The sourcing endpoint device may generate a priority value for the media feed, and the priority value may be transmitted to other members of the relay along with the input feed. Priority values of the different relay participants may be used by other devices, for example, intermediate servers or receiving endpoint devices, to manage aspects of the relay. For example, a relay server may prune streams from select endpoint devices based on relative priority values received from those devices. Alternatively, receiving endpoint devices may alter presentation of received feeds based on their associated priority values.

Abstract: Techniques are disclosed for coding and decoding video data using object recognition and object modeling as a basis of coding and error recovery. A video decoder may decode coded video data received from a channel. The video decoder may perform object recognition on decoded video data obtained therefrom, and, when an object is recognized in the decoded video data, the video decoder may generate a model representing the recognized object. It may store data representing the model locally. The video decoder may communicate the model data to an encoder, which may form a basis of error mitigation and recovery. The video decoder also may monitor deviation patterns in the object model and associated patterns in audio content; if/when video decoding is suspended due to operational errors, the video decoder may generate simulated video data by analyzing audio data received during the suspension period and developing video data from the data model and deviation(s) associated with patterns detected from the audio data.

Abstract: Techniques are presented for modifying images of an object in video, for example to correct for lens distortion, or to beautify a face. These techniques include extracting and validating features of an object from a source video frame, tracking those features over time, estimating a pose of the object, modifying a 3D model of the object based on the features, and rendering a modified video frame based on the modified 3D model and modified intrinsic and extrinsic matrices. These techniques may be applied in real-time to an object in a sequence of video frames.

Abstract: Image processing techniques may accelerate coding of viewport data contained within multi-view image data. According to such techniques, an encoder may shifting content of a multi-directional image data according to the viewport location data provided by a decoder. The encoder may code the shifted multi-directional image data by predictive coding, and transmit to the decoder, the coded multi-directional image data and data identifying an amount of the shift. Doing so may move the viewport location to positions in the image data that are coded earlier than the positions that the viewport location naturally occupies and, thereby, may accelerate coding. On decode, a decoder may compare its present viewport location with viewport location data provided by the encoder with coded video data. The decoder may decode the coded video data and extract a portion of the decoded video data corresponding to a present viewport location for display.

Abstract: A device implementing a system for audio-video conferencing using multiple stream identifiers includes a processor configured to receive, from a sending device, indication of a first content stream and a first stream identifier, and indication of a second content stream and a second stream identifier associated. The first content stream and the second content stream correspond to different bit rates of streaming content. The processor is configured to receive, from a receiving device, a request to subscribe to the second content stream, the request including the second stream identifier, and receive, from the sending device, an indication that the second stream identifier has been associated with the first content stream. The processor is configured to forward, to the receiving device, the first content stream based on the request to subscribe to the second content stream and on the indication that the second stream identifier has been associated with the first content stream.

Abstract: A device implementing the subject technology may include at least one processor configured to receive a plurality of buffer reports from a plurality of other devices, each of the plurality of buffer reports indicating a current target buffer level for a respective one of the plurality of other devices. The at least one processor may be further configured to determine a group target buffer level based at least in part on the current target buffer levels of the plurality of other devices and a current target buffer level of the at least one buffer. The at least one processor may be further configured to transmit the group target buffer level to the plurality of other devices. The at least one processor may be further configured to manage an occupancy of the at least one buffer based at least in part on the group target buffer level.

Abstract: A device implementing the subject technology may include at least one processor configured to transmit an allocation request requesting allocation of a group communication session with a plurality of devices and receive an allocation response in response to the allocation request, the allocation response including credential information for the device to use to join the group communication session. The at least one processor may be further configured to transmit an allocation bind request with the credential information to join the group communication session using the credential information and receive an allocation bind success response in response to the allocation bind request, the allocation bind success response indicating that the device has joined the group communication session. The at least one processor may be further configured to provide a join notification to the plurality of devices via an intermediary device to notify that the device has joined the group communication session.

Abstract: A device implementing the subject technology may include at least one processor configured to receive an indication of a task being performed at an other device. The at least one processor is further configured to perform, in response to receipt of the indication, one or more preliminary operations in anticipation of receiving a handoff of the task. The at least one processor is further configured to receive, after performing the one or more preliminary operations, a notification that the task is being handed off. The at least one processor is further configured to receive the handoff of the task from the other device. The at least one processor is further configured to continue to perform the task based at least in part on the one or more preliminary operations that were performed prior to receiving the notification that the task is being handed off.

Abstract: Methods are described for encoding and decoding blocks of image data using intra block copying (IBC). A source block for intra block copying is selected from a source region of a current image that is closer to the current block than a threshold, wherein the source region does not include a portion of the current image that is further from the current block than the threshold.

Abstract: Embodiments of the present invention provide techniques for coding video data efficiently based on detection of objects within video sequences. A video coder may perform object detection on the frame and when an object is detected, develop statistics of an area of the frame in which the object is located. The video coder may compare pixels adjacent to the object location to the object's statistics and may define an object region to include pixel blocks corresponding to the object's location and pixel blocks corresponding to adjacent pixels having similar statistics as the detected object. The coder may code the video frame according to a block-based compression algorithm wherein pixel blocks of the object region are coded according to coding parameters generating relatively high quality coding and pixel blocks outside the object region are coded according to coding parameters generating relatively lower quality coding.

Abstract: Techniques for encoding and decoding video images based on image content types are described. Techniques include determining a plurality of image content types from metadata or an image content type recognition algorithm, where each image content type corresponding to a portion of a source video, such as a spatial or temporal portion. Encoding parameters, such as quantization parameter, may be selected for portions of source by a constrained search for encoding parameters, where the constraints are based on image content type.

Abstract: Techniques are described for implementing format configurations for multi-directional video and for switching between them. Source images may be assigned to formats that may change during a coding session. When a change occurs between formats, video coders and decoder may transform decoded reference frames from the first format to the second format. Thereafter, new frames in the second configuration may be coded or decoded predictively using transformed reference frame(s) as source(s) of prediction. In this manner, video coders and decoders may use intra-coding techniques and achieve high efficiency in coding.

Abstract: Frame packing techniques are disclosed for multi-directional images and video. According to an embodiment, a multi-directional source image is reformatted into a format in which image data from opposing fields of view are represented in respective regions of the packed image as flat image content. Image data from a multi-directional field of view of the source image between the opposing fields of view are represented in another region of the packed image as equirectangular image content. It is expected that use of the formatted frame will lead to coding efficiencies when the formatted image is processed by predictive video coding techniques and the like.

Abstract: Techniques are disclosed for correcting artifacts in multi-view images that include a plurality of planar views. Image content the planar views may be projected from the planar representation to a spherical projection. Thereafter, a portion of the image content may be projected from the spherical projection to a planar representation. The image content of the planar representation may be used for display. Extensions are disclosed that correct artifacts that may arise during deblocking filtering of the multi-view images.

Abstract: Techniques are disclosed for coding high dynamic range (HDR) data. According to such techniques, HDR data may be converted to a domain of uniform luminance data. The uniform domain data may be coded by motion compensated predictive coding. The HDR data also may be coded by motion compensated predictive coding, using a coding parameter that is derived from a counterpart coding parameter of the coding of the uniform domain data. In another technique, HDR data may be coded using coding parameters that are derived from HDR domain processing but distortion measurements may be performed in a uniform domain.

Abstract: Techniques are disclosed for managing display of content from multi-view video data. According to these techniques, an object may be identified from content of the multi-view video. The object's location may be tracked across a sequence of multi-view video. The technique may extract a sub-set of video that is contained within a view window that is shifted in an image space of the multi-view video in correspondence to the tracked object's location. These techniques may be implemented either in an image source device or an image sink device.

Abstract: Chroma deblock filtering of reconstructed video samples may be performed to remove blockiness artifacts and reduce color artifacts without over-smoothing. In a first method, chroma deblocking may be performed for boundary samples of a smallest transform size, regardless of partitions and coding modes. In a second method, chroma deblocking may be performed when a boundary strength is greater than 0. In a third method, chroma deblocking may be performed regardless of boundary strengths. In a fourth method, the type of chroma deblocking to be performed may be signaled in a slice header by a flag. Furthermore, luma deblock filtering techniques may be applied to chroma deblock filtering.

Abstract: Embodiments of the present disclosure provide systems and methods for perspective shifting in a video conferencing session. In one exemplary method, a video stream may be generated. A foreground element may be identified in a frame of the video stream and distinguished from a background element of the frame. Data may be received representing a viewing condition at a terminal that will display the generated video stream. The frame of the video stream may be modified based on the received data to shift of the foreground element relative to the background element. The modified video stream may be displayed at the displaying terminal.

Abstract: Coding and decoding techniques are disclosed in which a plurality of coding parameter sets is transmitted between an encoder and a decoder, each of which is distinguishable from the others by a respective identifier. When a new frame of video is to be coded, an encoder may identify a coding parameter set to be applied during coding, it may code the new frame according to the identified coding parameter set, and it may transmit the coded frame to the decoder along with an identifier of the coding parameter set used during the coding. A plurality of coding parameter sets is persistent at an encoder and the decoder simultaneously.

Abstract: Techniques are disclosed for coding and decoding video captured as cube map images. According to these techniques, padded reference images are generated for use during predicting input data. A reference image is stored in a cube map format. A padded reference image is generated from the reference image in which image data of a first view contained in reference image is replicated and placed adjacent to a second view contained in the cube map image. When coding a pixel block of an input image, a prediction search may be performed between the input pixel block and content of the padded reference image. When the prediction search identifies a match, the pixel block may be coded with respect to matching data from the padded reference image. Presence of replicated data in the padded reference image is expected to increase the likelihood that adequate prediction matches will be identified for input pixel block data, which will increase overall efficiency of the video coding.