Comcast Cable Communications, LLC

Future Wei Technologies, Inc.

Vid Scale, Inc.

Interdigital Patent Holdings, Inc.

Other

Huawei Technologies Co., Limited

Alexander Giladi

Dan Grois

Weidong Mao

Xin Ru Wang

Yasser Fouad Syed

Shaobo Zhang

Alex Balk

Xin Liu

Peiyun Di

Tao Liu

Yongliang Liu

Yangpo Xu

Jiang Xu

Ali C Begen

Changquan Ai

Christopher Lintz

Blake Orth

Robert Ford

Xin Wang

Ali Begen

Ali Cengiz Begen

Systems, apparatuses, and methods are described for encoding a scene of media content based on visual elements of the scene. A scene of media content may comprise one or more visual elements, such as individual objects in the scene. Each visual element may be classified based on, for example, the motion and/or identity of the visual element. Based on the visual element classifications, scene encoder parameters and/or visual element encoder parameters for different visual elements may be determined. The scene may be encoded using the scene encoder parameters and/or the visual element encoder parameters.

Scene classification and learning for video compression

Systems and methods are described herein for processing video data. An encoder may transmit information indicating a duration that a particular frame should be displayed. The information may comprise an indication of whether the particular frame should be displayed for an increased duration. The encoder may decide during encoding, a whether the particular frame should be displayed for an increased duration (e.g., doubled, tripled, or more). The decision may be based on a similarity analysis performed by the encoder on two or more frames. Information indicating the decision may be inserted into a message, which may then be transmitted in a transport stream comprising encoded video data to a decoder. The decoder may decode the information and cause a display device to display the particular frame for the increased duration.

Method and apparatus for content-adaptive frame duration extension

Systems and methods are described herein for coordinating transcoders. Content may be received from different sources to be transcoded. Each transcoder of a plurality of transcoders may send data associated with content to each other to coordinate the plurality of transcoders. The data may indicate timing information for the encoded content and features of the content such as, for example, color, frame similarity, or frame type. The transcoders, while outputting encoded content, may coordinate either directly or via a broker. The transcoders may coordinate in order to synchronize their output so that frames, that may be received by each transcoder at different times, are aligned based on the timing information. The coordination and synchronization may improve error resilience. In the case of a transcoder/encoder or a site failure, there may be a seamless transition to a different transcoder/encoder and no reduction in performance because of the time alignment.

Method and apparatus for content-driven transcoder coordination

The present methods, systems, and apparatuses may provide for more efficient transmission and storage of initialization segments for individual content items that share a set of common parameters. Instead of generating initialization segments that are specific to each content item, a common initialization segment for the content items and/or an existing initialization segment for one of the content items may be used for initializing playback of one or more content segments for any of the content items sharing the set of common parameters.

Methods, systems, and apparatuses for improved content storage

Methods, systems, and apparatuses are described for encoding video. Video content to be encoded and sent to a computing device may be downscaled into one or more layers. The one or more layers may represent one or more versions of the video content such as one or more versions encoded at different resolutions. The residuals between each layer and the base layer may be upscaled so that one or more parameters associated with optimizing the encoding of the one or more layers may be determined by one or more neural networks based on the downscaling and upscaling process. The residuals between each layer, the one or more parameters, and the base layer may be encoded and sent to a computing device for decoding and playback of the video content using any of the versions of the video content.

Methods, systems, and apparatuses for content-adaptive multi-layer coding based on neural networks

Systems, methods, and apparatuses are described for compressing digital content. The digital content may comprise a plurality of frames. The plurality of frames may comprise a plurality of crossfade frames. A first boundary frame of the crossfade frames may be determined. A second boundary frame of the crossfade frames may be determined. At least a portion of the crossfade frames may be coded as inter-predicted frames using a weighting factor and based on the first boundary frame or the second boundary frame.

Systems and methods for compressing video

A first quantization value for encoding at least one frame of a content item may be determined based at least on a predetermined bitrate and a point in the content item associated with a scene change. A first duration associated with a first portion of the content item may be determined. The first portion of the content item may comprise the at least one frame and may be associated with the first quantization value. A second quantization value for encoding at least another frame of the content item may be determined based at least on the predetermined bitrate. A second duration associated with a second portion of the content item may be determined. The second portion of the content item may comprise the at least another frame and may be associated with the second quantization value.

Processing video using masking windows

Methods, systems, and apparatuses may encode a media content item based on metadata from previous encoding. The encoding may also generate encoding metadata, which may comprise a qualitative or quantitative characterization of the encoded media content item. A prediction engine may, based on this metadata, determine new encoding settings for the same or a different video resolution. The prediction engine may cause an encoded media content item to be stored and may cause encoding of the media content item using the new encoding settings.

Content-aware predictive bitrate ladder

Systems, apparatuses, and methods are described for filtering and/or removing defects from content, such as high dynamic range (HDR) content. A plurality of parameters for filtering one or more pixels may be determined. The parameter(s) may be used to determine one or more filter weights, and the filter weight(s) may be applied to one or more pixels and one or more corresponding prior pixels to generate one or more filtered pixels. The filtered content and/or pixels thereof may later be encoded for storage and/or transmission to users.

Pixel filtering for content

Systems, methods, and apparatuses are described for processing video. A method may comprise receiving video content comprising a plurality of frames and determining a splitting parameter of a partitioning of at least a portion of a first frame of the plurality of frames. Deblock filtering may be implemented on at least the first frame of the plurality of frames based at least on the splitting parameter.

Systems, methods, and apparatuses for processing video

An encoder may determine a plurality of coding units associated with a frame of a media file and a plurality of prediction units associated with the frame of the media file. The encoder may determine, based on the plurality of coding units associated with the frame and the plurality of prediction units associated with the frame, and based on a training of the encoder using one or more neural networks, that a particular region of the frame can be encoded using one or more encoding characteristics that are different than the encoding characteristics of one or more other particular regions of the frame. The encoder may allocate one or more encoding resources to the particular region of the frame based on the one or more encoding characteristics of the particular region of the frame in order to reduce the overall media bitrate.

Processing media using neural networks

Methods and systems are described for managing content. A content asset may be stored as a plurality of content segments. The plurality of content segments may comprise one or more identifiers that may be used to generate a manifest file for playback of the content asset.

Content information for manifest determination

Methods and systems for in-loop filtering may comprise receiving a video comprising at least one frame. The frame may comprise at least one block of pixels. A content complexity of the block of pixels may be determined. A viewing characteristic of the video may be determined. A number of borders to be filtered may be determined based on at least one of the content complexity or the viewing characteristic. A deblocking filter strength may be determined based on at least one of the content complexity or the viewing characteristic. The number of borders of the block of pixels may be filtered according to the deblocking filter strength.

Systems and methods for deblocking filtering

Systems, methods, and devices relating to video encoding for low-concurrency video channels are described herein. A video processing system may receive a manifest request for an encoded video stream associated with a selected channel. Based on the manifest request, the video processing system may request for a real-time linear (RTL) encoder to be started to encode the input compressed video stream for the channel in real-time. Also based on the manifest request, the video processing system may assign a faster-than-real-time (FTRT) encoder from a pool of already-running FTRT encoders to encode the video stream in real-time until the RTL encoder is fully started. The FTRT encoder may encode at a lower quality level to enable expedited real-time encoding. Based on the RTL encoder being fully started, the video processing system may switch the encoding from the FTRT encoder to the RTL encoder. The FTRT encoder may be returned to the FTRT encoder pool.

Video encoding for low-concurrency linear channels

An encoder (e.g., a Versatile Video Coding (VVC) encoder, etc.) may make real-time encoding decisions to vary a bitrate of a content item (e.g., high-resolution video, streaming content, a movie, a show/program, etc.) by upsampling and/or downsampling portions (e.g., frames/slices, group of pictures (GOP), coding units (CU), coding tree units (CTU), etc.) based on a cost function that utilizes a versatile Lagrangian multiplier (denoted as λto denote the versatility). The versatile Lagrangian multiplier may not only account for the effects of quantization (e.g., a quantization parameter (QP), etc.) on portions of the content item, instead, the versatile Lagrangian multiplier may also be based on adjustment parameters associated with content resolution and/or playback quality of experience (QoE). The versatile Lagrangian multiplier enables a substantial decrease in transmission bitrate for portions of a content item without reducing the visual presentation quality and keeping an end-user quality of experience (QoE) at an optimal level.

Growing community of inventors

Princeton, NJ, United States of America

Alexander Giladi