Abstract: Video processing such as encoding and/or decoding a picture can involve deriving an inter-prediction parameter based on first and second merge candidates used to generate a pairwise merge candidate, wherein the inter-prediction parameter comprises at least one of an index for weighted bi-prediction or an interpolation filter index; and encoding at least a portion of the picture information based on the inter-prediction parameter.

Abstract: Video decoder comprising a decoding core (94) configured to reconstruct a decoded picture using motion compensated prediction and transform-based residual decoding from one or more video coding units (100) within an access unit, AU, of a video data stream to obtain a reconstructed version (46a) of the decoded picture; an in-loop filter (90) configured to filter the reconstructed version of the decoded picture to obtain a version (46b) of the decoded picture to be inserted into the decoded picture buffer (92), DPB, of the video decoder; and a parametrizer configured to parametrize the in-loop filter by reading in-loop filter control information for parametrizing the in-loop filter from one or more parameter sets (102, 104) located within the access unit, AU, of the decoded picture which follow, along data stream order, the one or more video coding units (100), and/or a portion (106) of the one or more video coding units (100) following, along data stream order, data (108) comprised by the one or more video cod

Abstract: A decoder configured to decode residual levels, and sequentially dequantize the residual levels by selecting a quantizer out of a set of default quantizers depending on a current transition state, and updating the current transition state depending on a current residual level's characteristic obtained by an application of a binary function onto the current residual level, and depending on a quantization mode information contained in the data stream. The current transition state transitions, according to a surjective mapping which depends on the quantization mode information, from a domain of combinations of a set of one or more transition states with the current residual level's characteristic onto the set of one or more transition states, wherein a cardinality of the set of one or more transition states differs depending on the quantization mode information.

Abstract: Techniques for switching a client device to play low latency content are described. In accordance with various embodiments, the client device switching method is performed at a device (e.g., a client device) with a processor and a non-transitory memory. The client device detects a request for a user interface (UI) while playing a media content item from a buffer and sends to a server the request and status of playing the media content item from the buffer. The client device then receives from the server a switch point determined by the server based at least in part on the status and the requested UI. The client device further determines whether the buffer has sufficient UI frames rendered by the server at the switch point. Upon determining that the buffer has sufficient UI frames, the client device switches to playing the UI frames from the buffer at the switch point.

Abstract: A system architecture and methods for streaming or live video that can provide sub-second video over WebRTC to viewers with a horizontally scaling architecture. In some embodiments, the system and methods described generate video from another source on a server and redistribute it to client devices in a peer-to-peer architecture. The system and architecture are designed to deliver WebRTC to users but does not require broadcasters to change the systems and protocols they are familiar with and comfortable with using. Embodiments are directed to providing streaming audio and/or video content through an architecture that can ingress (intake) RTMP format content and egress (output and distribute) WebRTC format content efficiently by generating a client-side peer and client-side content on a server.

Abstract: Systems and methods for compression of data that exhibits mixed compressibility, such as floating-point data, are provided. As one example, aspects of the present disclosure can be used to compress floating-point data that represents the values of parameters of a machine-learned model. Therefore, aspects of the present disclosure can be used to compress machine-learned models (e.g., for reducing storage requirements associated with the model, reducing the bandwidth expended to transmit the model, etc.).

Abstract: A video coding mechanism is disclosed. The mechanism includes receiving a bitstream comprising one or more layers and a scalable nesting supplemental enhancement information (SEI) message. The scalable nesting SEI message includes one or more scalable-nested SEI messages and a scalable nesting output layer set (OLS) flag. The scalable nesting OLS flag is set to specify whether the scalable-nested SEI messages apply to specific OLSs or specific layers. A coded picture is decoded from the one or more layers to produce a decoded picture. The decoded picture is forwarded for display as part of a decoded video sequence.

Abstract: A method for decoding a video according to the present invention may comprise: decoding information indicating whether a non-zero transform coefficient exists in a current block, when the information indicates that the non-zero transform coefficient exists in the current block, determining a scanning order of the current block, and decoding a transform coefficient included in the current block according to the determined scanning order.

Abstract: The present disclosure relates to systems and methods for video decoding with a video decoding chip. The video decoding chip may include one or more input channels and one or more output channels. The systems and methods may include detecting a flag bit of each of the one or more input channels. The flag bit of an input channel may indicate a status of receiving its corresponding stream of encoded video data. The systems and methods may include determining an operating state of the one or more input channels based on the flag bits. The operating state of an input channel may include an open state and a closed state of the input channel. The systems and methods may further include determining at least one of the one or more output channels to output the corresponding stream of decoded video data based on the input channels in the open state.

Abstract: A method of decoding is provided. The method includes receiving a sub-bitstream having a sequence parameter set (SPS) with a profile tier level (PTL) syntax structure for an output layer set (OLS) with only one layer; setting a number of layers in the OLS equal to one based on the OLS having the only one layer; obtaining the PTL syntax structure for the OLS with the only one layer from the SPS when the number of layers in the OLS has been set equal to one; and decoding a picture from the only one layer using the PTL syntax structure to obtain a decoded picture. A corresponding method of encoding is also provided.

Abstract: Methods and apparatuses for signaling decoding data in a video bitstream, wherein one uses a syntax element indicating whether the decoding data are explicitly coded in the video bitstream or inferred from previous data of the video bitstream. A bitstream, a computer-readable storage medium and a computer program product are also described.

Abstract: A video coding mechanism is disclosed. The mechanism includes encoding a coded layer video sequence (CLVS) for a layer in a bitstream. A sequence parameter set (SPS) referred to by the CLVS is also encoded into the bitstream. The SPS is constrained to have a network abstraction layer (NAL) unit header layer identifier (nuh_layer_id) value equal to a nuh_layer_id value of the CLVS when the layer does not use inter-layer prediction. The bitstream is stored for communication toward a decoder.

Abstract: A method of decoding is provided. The method includes receiving, by the video decoder, a video bitstream including a video parameter set (VPS) and a plurality of layers, where each layer is included in at least one output layer set (OLS) specified by the VPS; and decoding, by the video decoder, a picture from one of the plurality of layers. A method of encoding is also provided. The method of encoding includes generating, by the video encoder, a plurality of layers and a video parameter set (VPS) specifying one or more output layer sets (OLSs), wherein each layer from the plurality of layers is included in at least one of the OLSs specified by the VPS; encoding, by the video encoder, the plurality of layers and the VPS into a video bitstream; and storing, by the video encoder, the video bitstream for communication toward a video decoder.

Abstract: A method of coding performed by a decoding device and a decoder are disclosed. The method comprises: obtaining a bitstream for a current picture; obtaining a quantity of tiles in a tile row of the current picture; obtaining a value of an address of a current slice, the current slice is comprised in the current picture; obtaining a value of a horizontal coordinate according to the value of the address of the current slice; parsing an indication value for a slice width from the bitsteam for the current picture, when a difference value between the quantity of tiles in the tile row of the current picture and the value of the horizontal coordinate is not equal to a first threshold.

Abstract: Methods and apparatuses for video coding are provided. The method includes that a decoder receives a first syntax element in picture parameter sets (PPS) specifying whether a picture corresponding to the PPS comprises one or more network abstraction layer (NAL) units and whether the one or more NAL units have a same NAL unit type, receives a second syntax element in a picture header (PH) specifying whether the picture corresponding to the PH is an intra random access point (IRAP) picture or a gradual intra refreshing (GDR) picture, and determines a value of the first syntax element based on a value of the second syntax element or determines the value of the second syntax element based on the value of the first syntax element.

Abstract: In a method and a device for encoding or decoding an image according to the present invention, motion information for bidirectional prediction of a current block may be derived on the basis of an inter mode previously defined in the device for encoding or decoding an image, and inter prediction may be performed on the current block on the basis of the motion information, wherein the motion information for bidirectional prediction is adjusted to be motion information for unidirectional prediction according to the predefined inter mode.

Abstract: Techniques and tools for reducing latency in video encoding and decoding by constraining latency due to reordering of video frames, and by indicating the constraint on frame reordering latency with one or more syntax elements that accompany encoded data for the video frames. For example, a real-time communication tool with a video encoder sets a syntax element that indicates a constraint on frame reordering latency, which is consistent with inter-frame dependencies between multiple frames of a video sequence, then outputs the syntax element. A corresponding real-time communication tool with a video decoder receives the syntax element that indicates the constraint on frame reordering latency, determines the constraint on frame reordering latency based on the syntax element, and uses the constraint on frame reordering latency to determine when a reconstructed frame is ready for output (in terms of output order).

Abstract: Systems and methods for coding and decoding are provided. A method includes encoding a video stream including video data partitioned into a plurality of layers, wherein the encoding includes determining whether a first picture of the video stream is to be output based on a syntax element that indicates a mode of output layer set signaling.

Abstract: According to the present disclosure, ALF parameters and/or LMCS parameters can be hierarchically signaled, which enables a reduction in the amount of data to be signaled for video/image coding and an increase in the coding efficiency.

Abstract: Methods, apparatus, systems and articles of manufacture for texture based immersive video coding are disclosed. An example apparatus includes a correspondence labeler to (i) identify first unique pixels and first corresponding pixels included in a plurality of pixels of a first view and (ii) identify second unique pixels and second corresponding pixels included in a plurality of pixels of a second view; a correspondence patch packer to (i) compare adjacent pixels in the first view and (ii) identify a first patch of unique pixels and a second patch of corresponding pixels based on the comparison of the adjacent pixels and the correspondence relationships, the second patch of corresponding pixels tagged with a correspondence list identifying corresponding patches in the second view; and an atlas generator to generate at least one atlas to include in encoded video data, the encoded video data not including depth maps.

Abstract: An apparatus for receiving a video data stream as an input bitstream is provided. The video data stream has a video encoded thereinto, wherein, for a playback speed modification factor (Nx), the apparatus is to determine a decoding capability requirement depending on a decoding capability requirement limit, wherein the playback speed modification factor (Nx) is a forward playback speed modification factor or is a backward playback speed modification factor.

Abstract: The present technology relates to a reproduction device, a reproduction method, and a recording medium capable of suppressing influence of motion parallax and image distortion. There is provided a reproduction device including an image processing unit that performs processing including: projecting an image captured from a specific position in a real space on a projection surface arranged according to a reference position set in a virtual space; acquiring a head movement amount of a user viewing the projected image; changing, according to the head movement amount with respect to the reference position in a first direction that is at least one of a left-right direction or an up-down direction as viewed from the user, a first relative distance between the reference position and a user position in the first direction; changing, according to the head movement amount with respect to the reference position.

Abstract: A method, device, and non-transitory computer-readable medium for decoding an encoded video bitstream using at least one processor, including, based on a number of at least one subpicture of a current picture being greater than one, obtaining a flag indicating whether subpicture partitioning information is explicitly signaled; based on the flag indicating that the subpicture partitioning information is explicitly signaled, obtaining the subpicture partitioning information; and decoding the current picture based on the subpicture partitioning information.

Abstract: A computer-implemented method, system and computer program product for compressing video. A set of video frames is partitioned into two subsets of different types of frames, a first type and a second type. The first type of frames of videos is compressed to generate a first representation by a first stage encoder. The first representation is then decoded to reconstruct the first type of frames using a first stage decoder. The second type of frames of video is compressed to generate a second representation that only contains soft edge information by a second stage encoder. A generative model corresponding to a second stage decoder is then trained using the first representation and the reconstructed first type of frames by using a discriminator employed by a machine learning system. After training the generative model, it generates reconstructed first and second types of frames using the soft edge information.

Abstract: A method, device, and non-transitory computer-readable medium for decoding an encoded video bitstream using at least one processor, including, obtaining from the encoded video bitstream a first flag indicating that reference picture resampling is enabled for coded video sequence (CVS); determining a value of a second flag indicating whether a picture resolution is changed in the CVS; based on the value of the second flag indicating that the picture resolution is changed in the CVS, decoding the CVS using the reference picture resampling for spatial scalability and adaptive resolution change (ARC); and based on the value of the second flag indicating that the picture resolution is not changed in the CVS, decoding the CVS using the reference picture resampling for the spatial scalability, and without using the reference picture resampling for the ARC.

Abstract: A method performed by a decoder for decoding a bitstream comprising a picture parameter set, PPS, and a first set of slices. The method includes obtaining the picture parameter set. The method also includes decoding a syntax element included in the picture parameter set to obtain an indicator value. The decoder is configured such that if the indicator value is set to a first value then the decoder determines that a picture header included in the bitstream comprises a parameter value corresponding to a particular parameter, otherwise the decoder determines that each slice included in the first set of slices comprises a parameter value corresponding to the particular parameter. If the picture header comprises the parameter value corresponding to the particular parameter, then this parameter value is used to decode slice data of each slice included in the first set of slices.

Abstract: Example video ingestion cables, display systems, and methods for harmonizing video formats for video ingestion are provided. An example video ingestion cable includes a first video interface connector cable to receive a first video feed formatted according to a first video format, a second video interface connector cable to receive a second video feed formatted according to a second video format, a format conversion circuit to convert the first video feed or the second video feed to a harmonized video format, and an output interface connector to transmit one of the first video feed and the second video feed as an output video feed formatted according to the harmonized video format to a display device. An example display system includes first and second video ingestion cables and a video ingestion circuit to select an input video feed for display.

Abstract: A method of processing video data includes determining that a non-linear adaptive loop filtering operation is applied for a current video region of a video; deriving a first filtering index for the current video region and deriving a first filtering parameter based on the first filtering index; deriving a first clipping parameter from a clipping parameter set based on the first filtering index; performing a clipping operation that is part of the non-linear adaptive loop filtering operation based on the first clipping parameter, where the first clipping parameter is used to clip differences between reference sample values of a current sample value of the current video region and the current sample value before applying the first filtering parameter; and performing a conversion between the current video region and a bitstream of the video based on the non-linear adaptive loop filtering operation.

Abstract: A method includes storing entries in a first first-in first-out (FIFO) buffer, each entry of the first FIFO buffer includes a respective segment of plural segments of a first data stream and timing attributes corresponding to the respective segment. The method also includes processing the respective segments in entries output from the first FIFO buffer using a first media processing task of a workflow in a network-based media processing (NBMP) system. The respective segments are processed independently from each other and the first media processing task is performed in a cloud computing environment. The method also includes generating a continuous data stream by concatenating the processed segments according to the timing attributes corresponding to the processed segments.

Abstract: Provided is a method of providing a user interface for video retrieval performed by a computing device, the method including: receiving a search query, providing a search result interface displaying at least one search video content and search section searched by the search query, wherein the search video content and the search section are related with at least one of a plurality of video semantic search attributes corresponding to the search query, and providing a timeline view interface for the search video content when it is determined to display the search result interface according to a timeline view mode, wherein the timeline view interface has a visual characteristic indicating the degree of relevance to at least one of the plurality of video semantic search attributes corresponding to the search query.

Abstract: A three-dimensional data encoding method includes: dividing point cloud data into pieces of sub point cloud data by dividing a three-dimensional space into subspaces; shifting each of the pieces of sub point cloud data in accordance with a predetermined shift amount; and generating a bitstream by encoding the pieces of sub point cloud data shifted. The bitstream includes first control information common to the pieces of sub point cloud data, and pieces of second control information for each of the pieces of sub point cloud data, the first control information including first information about a shift amount of each of the pieces of sub point cloud data.

Abstract: The present invention relates to a method and a device for decoding an image, which improve encoding and decoding efficiency by performing various forms of transform and inverse transform during transform and inverse transform processes of a video coding technique.

Abstract: A video coding mechanism is disclosed. The mechanism includes encoding a bitstream comprising one or more output layer sets (OLSs). A non-scalable-nested supplemental enhancement information (SEI) message is also encoded into the bitstream. The non-scalable-nested SEI message is constrained to apply only to a zeroth (0-th) OLS. The 0-th OLS includes only an output layer. A set of bitstream conformance tests are performed on the 0-th OLS based on the non-scalable-nested SEI message. The bitstream is stored for communication toward a decoder.

Abstract: An example method is provided to include receiving a media bitstream comprising one or more media units and a first enhancement information message, wherein the first enhancement information message comprises at least two independently parsable structures, a first independently parsable structure comprising information about at least one purpose of one or more neural networks (NNs) to be applied to the one or more media units, and a second independently parsable structure comprising or identifying one or more neural networks; decoding the one or more media units; and using the one or more neural networks to enhance or filter one or more frames of the decoded the one or more media units, based on the at least one purpose. An example method includes. Corresponding apparatuses and computer program products are also provided.

Abstract: Techniques for publishing key pictures at a server and using the key picture information for operations on a client device are described herein. In accordance with various embodiments, the server creates an intermediate unit including key picture(s) from media content. The server then generates map(s) specifying for each key picture, a type, properties, and an association to the intermediate unit. The server also packages the intermediate unit into key picture unit(s) according to the map(s). The client device obtains a manifest for the media content referencing the key picture(s) and the type of each key picture. Upon receiving a request to perform operation(s) on a respective key picture, the client device obtains a corresponding key picture unit and parses the manifest to determine a respective type. Based on the respective type matches a criterion, the client device performs the operation(s) on the key picture unit.

Abstract: A video coding mechanism is disclosed. The mechanism includes receiving a bitstream comprising a flag and a plurality of coded pictures including an intra random access point (IRAP) picture and one or more non-leading pictures associated with the IRAP picture. When the flag is set to a first value any leading pictures associated with the IRAP picture precede, in decoding order, all non-leading pictures associated with the IRAP picture. When the flag is set to a second value a non-leading picture precedes, in decoding order, an initial leading picture associated with the IRAP picture. The IRAP picture, any leading pictures associated with the IRAP picture, and the one or more non-leading pictures associated with the IRAP picture are decoded in decoding order based on the flag.

Abstract: An image decoding method performed by a decoding device according to the present disclosure comprises the steps of: receiving a bitstream containing at least one of segmentation information of a current picture and prediction information for a current block included in the current picture; deriving a first segmentation structure of the current picture, which is based on multiple tiles, on the basis of the segmentation information of the current picture including at least one of information of the number of width-parsing columns, information of the last width, information of the number of height-parsing rows, and information of the last height; deriving a block predicted for the current block, on the basis of the prediction information for the current block contained in one of the multiple tiles; and generating reconstruction samples for the current block on the basis of the predicted block.

Abstract: Method and apparatus for carrying out the method receiving packets, each of the packets comprising a header and a payload. For a particular packet among the packets, the method includes processing at least the header of the particular packet to determine a flow associated with the particular packet; attempting to determine a payload structure based on the flow, the payload structure associated with transport of coded video data in the payload of the particular packet; and if the attempting is successful, repackaging coded video data contained in the payload of the particular packet into a new packet and forwarding the new packet to an external system or storing the new packet in memory.

Abstract: Apparatuses, systems, and techniques to classify content. In at least one embodiment, a mixture of neural networks each trained to generate labels for various types of input are used to automatically generate appropriate content labels given an input.

Abstract: This disclosure relates to video coding and more particularly to techniques for signaling subpicture information for coded video. In one example, a method of decoding video data comprises: receiving a general constraint information syntax elements; parsing a first syntax element from the general constraint information syntax elements specifying whether a constraint is imposed on the number of slices that being contained in each subpicture; receiving a picture parameter set syntax elements; and parsing a second syntax element from the picture parameter set syntax elements specifying that each sub-picture contains one and only one slice, wherein a value of the second syntax element is constrained according to the first syntax element parsed from the general constraint information syntax elements.

Abstract: Devices, systems and methods related to digital video coding, and specifically, to management of syntax flags with respect chroma formats are described. In one representative aspect, the disclosed technology may be used to provide a method for video decoding. The method includes determining a chroma format associated with a region of a video and determining, based on the chroma format, whether one or more syntax flags applicable to the region of the video are included in a syntax structure of a coded representation of the video. The one or more syntax flags are indicative of a joint chroma residual coding step for representing the region in the coded representation. The method also includes generating one or more decoded video blocks of the region by parsing the coded representation according to a presence or an absence of the one or more syntax flags in the coded representation.

Abstract: A video coding mechanism is disclosed. The mechanism includes receiving a bitstream comprising a sequence parameter set (SPS) including a SPS video parameter set identifier (sps_video_parameter_set_id). The bitstream also comprises a coded picture in a set of video coding layer (VCL) network abstraction layer (NAL) units associated with a layer having a NAL unit header layer identifier (nuh_layer_id). A general layer index corresponding to the nuh_layer_id (GeneralLayerIdx[nuh_layer_id]) is set equal to zero when the sps_video_parameter_set_id is equal to zero. The coded picture is decoded from the VCL NAL units based on the GeneralLayerIdx[nuh_layer_id] to produce a decoded picture The decoded picture is forwarded for display as part of a decoded video sequence.

Abstract: In example embodiments, an apparatus, a method, and a computer program product are provided. The apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: encode or decode a high-level bitstream syntax for at least one neural network; wherein the high-level bitstream syntax comprises at least one information unit, wherein the at least one information unit comprises syntax definitions for the at least one neural network or a portion of the at least one neural network; and wherein a serialized bitstream comprises one or more of the at least one information units.

Abstract: According to the disclosures of the present document, entry point-related information/parameter can be signaled by means of upper-level syntax, thereby allowing the amount of data necessary to be signaled for video/image coding to be reduced and coding efficiency to be increased.

Abstract: A video decoding method, a video encoding method, and related apparatuses. The method includes: determining a current video frame; determining a reference frame corresponding to the current video frame from video frames that have been decoded, and obtaining a target quantity of blocks that are decoded in a skip mode in the reference frame and a total block quantity of blocks in the reference frame; determining, according to a relationship between the target quantity and the total block quantity, a target resolution used for decoding the current video frame; and decoding the current video frame by using the target resolution. For different current video frames, different resolutions used for decoding can be adaptively selected, to simplify operations of determining the target resolution for decoding the current video frame, thereby resolving the technical problem of relatively low video encoding and decoding efficiency caused by complex processing operations in the related art.

Abstract: Methods and apparatuses for video encoding, comprising: receiving a video sequence; encoding the video sequence by using control flags for luma mapping with chroma scaling (LMCS) at a sequence level, a picture level, or a slice level, wherein the sequence level, the picture level, and the slice level are levels ranking from high to low; signaling a first control flag indicating whether the LMCS is enabled at a first level; and in response to the first control flag indicating the LMCS is enabled at the first level, signaling a second control flag indicating whether LMCS is enabled at a second level, wherein: the LMCS is enabled at the second level when a value of the second control flag equals to 1; the LMCS is disabled at the second level when the value of the second control flag equals to 0; and the second level is a lower level than the first level.

Abstract: The present embodiments introduce a new type of random access point in video bitstreams that can be used for random access operations but can be represented in encoded form at a lower bit-cost as compared to IRAP pictures. The random access point is a dependent random access point (DRAP) picture that is encoded and decoded using an IRAP picture and/or a previous, according to a decoding order, DRAP picture as sole reference picture(s) for the DRAP picture. The DRAP picture is encoded as a trailing picture that may be used for reference and constitutes a random access point in a video bitstream.

Abstract: An image decoding method is disclosed. The image decoding method includes determining a prediction mode of a current block based on prediction mode information of the current block obtained from a bitstream, obtaining a transform coefficient block of the current block from the bitstream, dequantizing the transform coefficient to generate a dequantized transform coefficient block, determining a transform kernel for the dequantized transform coefficient block, and generating a residual block of the current block by performing inverse transform on the dequantized transform coefficient block using the transform kernel.

Abstract: An image decoding method performed by a decoding apparatus, according to the present document, comprises the steps of: acquiring image information including a block-based delta pulse code modulation (BDPCM) constraint flag indicating whether or not BDPCM is constrained with respect to an image; acquiring BDPCM-associated information regarding a current block on the basis of the BDPCM constraint flag; and generating reconstructed samples for the current block on the basis of the BDPCM-associated information.

Abstract: This disclosure relates to video coding and more particularly to techniques for signaling temporal sub-layer information for coded video. According to an aspect of an invention, a range of a value of a third syntax element in a sequence parameter set is determined based on whether the sequence parameter set refers to a video parameter set, wherein the third syntax element specifies a maximum number of temporal sub-layers that is present in each coded video sequence referring to the sequence parameter set.