Apple Inc.

Texas Instruments Corporation

Chris Yoochang Chung

Hsi-Jung Wu

Xiaosong Zhou

Dazhong Zhang

Jiefu Zhai

Jae Hoon Kim

Yeping Su

James O Normile

Hang Yuan

Hyeonkuk Jeong

Yunfei Zheng

Ke Zhang

Joe S Abuan

Thomas Christopher Jansen

Jun Xin

Yan Yang

Peikang Song

Albert E Keinath

Mei Guo

Douglas Scott Price

Ming Chen

Gobind Johar

Shujie Liu

David R Conrad

Luciano Miguel Verger

Jingteng Xue

Gang Lu

Wen Zhao

Srinivasan Vasudevan

Feng Yi

Jun Xu

David L Biderman

James David Batson

Xiaojin Shi

John Y Su

Christian L Duvivier

Zhenheng Li

Ionut Hristodorescu

Xingyu Zhang

Jochen Christian Schmidt

Hao Pan

Roberto Garcia

Yao-Chung Lin

Sundararaman V Shiva

Yuxin Liu

Sudeng Hu

Xing Wen

Paul Seung Ho Chang

James Oliver Normile

Thomas Jansen

Techniques are disclosed by which a coding parameter is determined to encode video data resulting in encoded video data possessing a highest possible video quality. Features may be extracted from an input video sequence. The extracted features may be compared to features described in a model of coding parameters generated by a machine learning algorithm from reviews of previously-coded videos, extracted features of the previously-coded videos, and coding parameters of the previously-coded videos. When a match is detected between the extracted features of the input video sequence and extracted features represented in the model, a determination may be made as to whether coding parameters that correspond to the matching extracted feature correspond to a tier of service to which the input video sequence is to be coded. When the coding parameters that correspond to the matching extracted feature correspond to the tier of service to which the input video sequence is to be coded, the input video sequence may be coded according to the coding parameters.

Content adaptation for streaming

Techniques are disclosed for coding video data predictively based on predictions made from spherical-domain projections of input pictures to be coded and reference pictures that are prediction candidates. Spherical projection of an input picture and the candidate reference pictures may be generated. Thereafter, a search may be conducted for a match between the spherical-domain representation of a pixel block to be coded and a spherical-domain representation of the reference picture. On a match, an offset may be determined between the spherical-domain representation of the pixel block to a matching portion of the of the reference picture in the spherical-domain representation. The spherical-domain offset may be transformed to a motion vector in a source-domain representation of the input picture, and the pixel block may be coded predictively with reference to a source-domain representation of the matching portion of the reference picture.

Sphere projected motion estimation/compensation and mode decision

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.

Systems and methods for perspective shifting in video conferencing session

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.

Real-time face and object manipulation

Methods and Systems disclosed to counteract spatial distortions introduced by imaging processes of multi-directional video frames, where objects may be projected to spherical or equirectangular representations. Techniques provided to invert the spatial distortions in video frames used as reference picture data in predictive coding, by spatially transforming the image content of the reference picture data before this image content is being used for the prediction of input video data in prediction-based coders and decoders.

Processing of equirectangular object data to compensate for distortion by spherical projections

Techniques are disclosed for overcoming communication lag between interactive operations among devices in a streaming session. According to the techniques, a first device streaming video content to a second device and an annotation is entered to a first frame being displayed at the second device, which is communicated back to the first device. Responsive to a communication that identifies the annotation, a first device may identify an element of video content from the first frame to which the annotation applies and determine whether the identified element is present in a second frame of video content currently displayed at the first terminal. If so, the first device may display the annotation with the second frame in a location where the identified element is present. If not, the first device may display the annotation via an alternate technique.

Techniques to overcome communication lag between terminals performing video mirroring and annotation operations

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.

In loop chroma deblocking filter

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.

Object tracking in multi-view video

Techniques are disclosed for managing memory allocations when coding video data according to multiple codec configurations. According to these techniques, devices may negotiate parameters of a coding session that include parameters of a plurality of different codec configurations that may be used during the coding session. A device may estimate sizes of decoded picture buffers for each of the negotiated codec configurations and allocate in its memory a portion of memory sized according to a largest size of the estimated decoded picture buffers. Thereafter, the devices may exchange coded video data. The exchange may involve decoding coded data of reference pictures and storing the decoded reference pictures in the allocated memory. During the coding session, the devices may toggle among the different negotiated codec configurations. As they do, reallocations of memory may be avoided.

Dynamic video configurations

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.

Packed image format for multi-directional video

Computing devices may implement instant video communication connections for video communications. Connection information for mobile computing devices may be maintained. A request to initiate an instant video communication may be received, and if authorized, the connection information for the particular recipient mobile computing device may be accessed. Video communication data may then be sent to the recipient mobile computing device according to the connection information so that the video communication data may be displayed at the recipient device as it is received. New connection information for different mobile computing devices may be added, or updates to existing connection information may also be performed. Connection information for some mobile computing devices may be removed.

Instant video communication connections

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.

Video coding techniques for multi-view video

Growing community of inventors

Sunnyvale, CA, United States of America

Chris Yoochang Chung