Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: deriving, for a conversion between a video unit of a video and a bitstream of the video, a first set of local illumination compensation (LIC) parameters for the video unit based on spatial neighboring video units of the video unit or a template of the video unit; applying the first set of LIC parameters and a second set of LIC parameters during an illumination compensation associated with the video unit; and performing the conversion based on the illumination compensation.

IPC Classes  ?

• H04N 19/52 - Processing of motion vectors by encoding by predictive encoding

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: applying, for a conversion between a video unit of a video and a bitstream of the video, a combined filtering approach to a sample associated with the video unit, wherein the combined filtering approach comprises: a filtering approach and a bilateral filtering (BF) approach for a reference sample; and performing the conversion based on the filtered sample.

IPC Classes  ?

• H04N 19/82 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop
• H04N 19/117 - Filters, e.g. for pre-processing or post-processing

Abstract

A method for visual data processing comprises: performing a conversion between visual data and a bitstream of the visual data with a neural network (NN) -based model, a synthesis transform in the NN-based model comprising at least one upscaling layer, and each of the at least one upscaling layer being used for increasing a data dimension of respective input of the at least one upscaling layer.

IPC Classes  ?

• G06T 9/00 - Image coding

Abstract

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: performing a conversion between visual data and a bitstream of the visual data with a neural network (NN) -based model, a pooling layer in the NN-based model being configured to be applied with a padding operation that is used for padding at least one sample for an input tensor of the pooling layer.

IPC Classes  ?

• G06T 9/00 - Image coding

Abstract

A mechanism for processing video data is disclosed. The mechanism determines to pad at least one unavailable sample of a video before feeding the video into a process. A conversion is performed between a visual media data and a bitstream based on the padded samples.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• G06N 3/02 - Neural networks
• G06N 20/00 - Machine learning
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
• H04N 19/00 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: obtaining, for a conversion between the current video block and a bitstream of the video, a target number for a set of intra block copy merge mode with block vector difference (IBC-MBVD) candidates, the target number being indicated in the bitstream and dependent on a target configuration of a coding process for coding the current video block; selecting, based on the target number, the set of IBC-MBVD candidates from a plurality of IBC-MBVD candidates associated with an intra block copy (IBC) base candidate for the current video block; and performing the conversion based on the set of IBC-MBVD candidates.

IPC Classes  ?

• H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• H04N 19/119 - Adaptive subdivision aspects e.g. subdivision of a picture into rectangular or non-rectangular coding blocks
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining to infer that a value of a syntax element is equal to 0 when the syntax element is not present in a bitstream. The value of the syntax element plus one specifies a number of submeshes in each mesh frame. A conversion is performed between a visual media data and a bitstream based on the syntax element.

IPC Classes  ?

• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• G06T 9/00 - Image coding
• H04N 19/124 - Quantisation
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream

Abstract

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: determining, for a conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model, a first adjusting parameter from a first table based on a probability parameter sample associated with the visual data; adjusting a first sample associated with the visual data based on the first adjusting parameter; and performing the conversion based on the adjusted first sample.

IPC Classes  ?

• H04N 19/85 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
• G06N 3/02 - Neural networks
• G06N 20/00 - Machine learning
• H04N 19/00 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
• G06N 3/00 - Computing arrangements based on biological models

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining one or more bytes of data from a supplemental enhancement information (SEI) raw byte sequence payload (RBSP) header, wherein the SEI RBSP header is included in an SEI RBSP before one or more SEI messages carried in the SEI RBSP. A conversion is performed between a visual media data and a bitstream based on the SEI RBSP header.

IPC Classes  ?

• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/169 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
• H04N 19/196 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the adaptation method, adaptation tool or adaptation type used for the adaptive coding being specially adapted for the computation of encoding parameters, e.g. by averaging previously computed encoding parameters

Abstract

A method for point cloud coding, in the method, for a conversion between a current frame of a point cloud sequence and a bitstream of the point cloud sequence, a set of triangle meshes of the current frame are determined. A parameter for at least one projection plane for a triangle mesh of the set of triangle meshes is determined before voxelizing the triangle mesh. The conversion is performed based on the parameter.

IPC Classes  ?

• G06T 9/00 - Image coding

Abstract

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: performing a conversion between visual data and a bitstream of the visual data with a neural network (NN) -based model, a color transformation between an internal color format and an output color format associated with the conversion being allowed to be disabled.

IPC Classes  ?

• H04N 19/50 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
• H04N 19/13 - Adaptive entropy coding, e.g. adaptive variable length coding [AVLC] or context adaptive binary arithmetic coding [CABAC]
• G06N 3/02 - Neural networks

Abstract

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: performing a conversion between visual data and a bitstream of the visual data with a neural network (NN) -based model, wherein a first format for coding the visual data and a second format of output visual data from the conversion are indicated with different indications, the first format indicates a first relationship between a size of a first component of the coded visual data and a size of a second component of the coded visual data, and the second format indicates a second relationship between a size of a first component of the output visual data and a size of a second component of the output visual data.

IPC Classes  ?

• H04N 19/132 - Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking

Abstract

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: performing a first conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model, the first conversion comprising at least one of the following: converting, based on a first predetermined order, a first tensor having more than one dimension to a one-dimensional first array, the first tensor and the first array storing first data associated with the visual data, and the first predetermined order indicating a correspondence between samples of the first tensor and samples of the first array, or converting, based on a second predetermined order, a one-dimensional second array to a second tensor having more than one dimension, the second tensor and the second array storing second data associated with the visual data.

IPC Classes  ?

• H04N 19/103 - Selection of coding mode or of prediction mode
• H04N 19/1 -

Abstract

Embodiments of the present disclosure provide a solution for point cloud coding. A method for point cloud coding is proposed. In the method, for a conversion between a current frame of a point cloud sequence and a bitstream of the point cloud sequence, at least one prediction weight value of at least one neighbor sub-node of a current node of the current frame is determined. A node representing a spatial partition of the current frame. A sub-node represents a partition of a node. A target neighbor for predicting the current node is determined based on the at least one prediction weight value. A prediction of the current node is determined based on the target neighbor. The conversion is performed based on the prediction.

IPC Classes  ?

• H04N 19/597 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding specially adapted for multi-view video sequence encoding

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining to apply an adaptive coefficient precision for an adaptive loop filter (ALF). A conversion can then be performed between a visual media data and a bitstream based on the adaptive coefficient precision applied.

IPC Classes  ?

• H04N 19/82 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop

Abstract

Computing systems, computing apparatuses, computing methods, and computer program products are disclosed for machine learning ranking. An example computing method includes receiving a search query and determining a plurality of machine learning model execution engines based on the search query and a plurality of search result types. The example computing method further includes generating a plurality of subsets of search results based on the search query and the plurality of machine learning model execution engines. The example computing method further includes generating a set of search results comprising at least one search result from each of the plurality of subsets of search results.

IPC Classes  ?

• G06F 16/2457 - Query processing with adaptation to user needs
• G06N 5/04 - Inference or reasoning models
• G06N 20/00 - Machine learning

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between the current video block and a bitstream of the video, a target number for a set of motion candidates, the target number being smaller than or equal to an upper limit value; determining, based on the target number and a fast rate distortion optimization (RDO) process, the set of motion candidates from a plurality of motion candidates for an intra block copy (IBC) based mode for coding the current video block; and performing the conversion based on the set of motion candidates.

IPC Classes  ?

• H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
• H04N 19/103 - Selection of coding mode or of prediction mode
• H04N 19/147 - Data rate or code amount at the encoder output according to rate distortion criteria
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream

Abstract

A method for processing a video includes determining, for a first video unit, a set of local illumination compensation (LIC) parameters including a scaling factor and an offset factor; performing or skipping a pre-process on at least one parameter of the set of LIC parameters; and updating at least one history based local illumination compensation parameter table (HLICT) using at least one parameter of the set of LIC parameters, the at least one HLICT being used for a conversion of subsequent video units.

IPC Classes  ?

• H04N 19/46 - Embedding additional information in the video signal during the compression process
• H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• H04N 19/124 - Quantisation
• H04N 19/159 - Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: applying, for a conversion between a video unit of a video and a bitstream of the video, a filtering approach to a prediction sample associated with the video unit;and performing the conversion based on the filtered prediction sample.

IPC Classes  ?

• H04N 19/82 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop
• H04N 19/117 - Filters, e.g. for pre-processing or post-processing

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: obtaining, for a conversion between a current block of a video and a bitstream of the video, a chroma fusion candidate for the current block; and performing the conversion based on the chroma fusion candidate.

IPC Classes  ?

• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: deriving, for a conversion between a current block of a video and a bitstream of the video, at least one of: a filter or a model based on decoding information; applying the at least one of: the filter or the model to coding of at least one of: the current block or a future block; and performing the conversion based on the at least one of: the filter or the model.

IPC Classes  ?

• H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

A mechanism for processing video data is disclosed. A determination is made to resize an image with a first size to create a resized image with a second size. A conversion is performed between a visual media data and a bitstream based on the resized image. The conversion includes applying a neural network-based coding model to the resized image to achieve variable rate neural network-based compression.

IPC Classes  ?

• H04N 19/149 - Data rate or code amount at the encoder output by estimating the code amount by means of a model, e.g. mathematical model or statistical model
• H04N 19/122 - Selection of transform size, e.g. 8x8 or 2x4x8 DCTSelection of sub-band transforms of varying structure or type
• H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component

Abstract

Motion compensation along different directions is disclosed. A method for video processing includes determining, for a conversion between a current video block of a video and a bitstream representation of the current video block, optical flow associated with the current video block in an optical flow-based motion refinement process or prediction process. The optical flow is derived along directions that are different from a horizontal direction and/or a vertical direction. The method also includes performing the conversion based on the optical flow.

IPC Classes  ?

• H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determine, for a conversion between a video unit of a video and a bitstream of the video, that a first syntax element (SE) related to geometric partitioning mode (GPM) is coded with a plurality of contexts; and performing the conversion based on the first SE.

IPC Classes  ?

• H04N 19/50 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/10 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
• H04N 19/00 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining an identifying number or a syntax element named po_id is signalled in the SEI processing order SEI message to identify a group of SEI message types for which the preferred order of processing is indicated in the SEI processing order SEI message. A conversion is performed between a visual media data and a bitstream based on the syntax element.

IPC Classes  ?

• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
• H04N 19/00 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining that, except for one or more special cascading cases, any processing chain containing multiple supplemental enhancement information (SEI) message types is indicated by an SEI processing order (SPO) SEI message having a particular value of a processin order identifier syntax element. A conversion is performed between a visual media data and a bitstream based on the SPO SEI message.

IPC Classes  ?

• H04N 19/46 - Embedding additional information in the video signal during the compression process
• H04N 19/40 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using video transcoding, i.e. partial or full decoding of a coded input stream followed by re-encoding of the decoded output stream
• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/44 - Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder
• H04N 21/23 - Processing of content or additional dataElementary server operationsServer middleware
• H04N 13/172 - Processing image signals image signals comprising non-image signal components, e.g. headers or format information

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining preprocessing information including properties or parameters of optimizing filters is included in a bitstream. A conversion is performed between a visual media data and a bitstream based on the preprocessing information.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/635 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding using sub-band based transform, e.g. wavelets characterised by filter definition or implementation details
• H04N 19/40 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using video transcoding, i.e. partial or full decoding of a coded input stream followed by re-encoding of the decoded output stream
• H04N 19/80 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
• G06F 11/30 - Monitoring

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining to apply a chosen processing chain to a picture, wherein the chosen processing chain includes applying one or more post-processing filters (PPFs) to the picture. The PPFs may include neural-network post-filters (NNPFs). A conversion is performed between a visual media data and a bitstream based on the PPFs.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/635 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding using sub-band based transform, e.g. wavelets characterised by filter definition or implementation details
• H04N 19/80 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
• H04N 19/187 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a scalable video layer

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. In the method, for a conversion between a current video block of a video and a bitstream of the video, affine information of the current video block is determined based on first affine information of a first block of the video. The first block is coded with a first coding tool different from an affine coding tool. A prediction of the current video block is determined based on the affine information. The conversion is performed based on the prediction.

IPC Classes  ?

• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

Embodiments of the present disclosure provide a solution for point cloud coding. A method for point cloud coding is proposed. In the method, for a conversion between a current frame of a point cloud sequence and a bitstream of the point cloud sequence, a prediction mode for a region of the current frame is determined. The prediction mode at least comprises a first mode based on an intra prediction and an inter prediction. A prediction of the region is determined based on the prediction mode. The conversion is performed based on the prediction.

IPC Classes  ?

• G06T 9/00 - Image coding

Abstract

A method implemented by a video coding apparatus. The method includes applying a neural network (NN) filter to an unfiltered sample of a video unit to generate a filtered sample. The NN filter includes an NN filter model generated based on partitioning information of the video unit. Usage of the NN filter is indicated by one or more syntax elements in a bitstream. A conversion is performed between a video media file and a bitstream based on the filtered sample.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/82 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: applying, for a conversion between a video unit of a video and a bitstream of the video, a connection to a plurality of filters; applying the plurality of filters with the connection in combination to the video unit; and performing the conversion based on the filtered video unit.

IPC Classes  ?

• H04N 19/82 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop
• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component
• H04N 19/86 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression involving reduction of coding artifacts, e.g. of blockiness

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. In the method, for a conversion between a current video block of a video and a bitstream of the video, a first prediction of the current video block is determined based on a first coding tool. The first coding tool comprises a motion vector difference (MVD) -related coding tool. A third prediction of the current video block is determined based on the first prediction and a second prediction of the current video block. The second prediction is determined based on a second coding tool different from the first coding tool. The conversion is performed based on the third prediction.

IPC Classes  ?

• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

Embodiments of the present disclosure provide a solution for point cloud processing. A method for point cloud processing is proposed. The method comprises: determining, for a conversion between a current point cloud (PC) sample of a point cloud sequence and a bitstream of the point cloud sequence, a prediction for a current feature of the current PC sample based on a current sparse PC sample of the current PC sample, a set of sparse PC samples and a set of features of at least one reference PC sample of the current PC sample; and performing the conversion based on the prediction for the current feature.

IPC Classes  ?

• G06T 9/00 - Image coding

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining to use only a luma channel to convey displacement data when the displacement data is coded in a 4:4:4 video format. A conversion is performed between a visual media data and a bitstream based on the displacement data.

IPC Classes  ?

• H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component
• H04N 19/463 - Embedding additional information in the video signal during the compression process by compressing encoding parameters before transmission
• H04N 19/11 - Selection of coding mode or of prediction mode among a plurality of spatial predictive coding modes
• H04N 19/137 - Motion inside a coding unit, e.g. average field, frame or block difference
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/85 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
• H04N 19/51 - Motion estimation or motion compensation

Abstract

A mechanism for processing video data is disclosed. The mechanism determines for a supplemental enhancement information (SEI) processing order SEI message that SEI prefix indications, when present, are signaled in units of bits, where an SEI prefix indication for a particular SEI payloadType is a bit string that follows an SEI payload syntax of that value of payloadType and contains a number of complete syntax elements starting from a first syntax element in an SEI payload. A conversion is performed between a visual media data and a bitstream based on the SEI processing order SEI message.

IPC Classes  ?

• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/46 - Embedding additional information in the video signal during the compression process
• H04N 19/40 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using video transcoding, i.e. partial or full decoding of a coded input stream followed by re-encoding of the decoded output stream
• H04N 19/44 - Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder
• H04N 21/23 - Processing of content or additional dataElementary server operationsServer middleware
• H04N 13/172 - Processing image signals image signals comprising non-image signal components, e.g. headers or format information

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining multiple neural-network post-filters (NNPFs) or neural-network post-processing filter groups (NNPFGs) defined in one or more supplemental enhancement information (SEI) messages share a same NNPF purpose. A conversion is performed between a visual media data and a bitstream based on the NNPF purpose.

IPC Classes  ?

• H04N 19/46 - Embedding additional information in the video signal during the compression process
• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/85 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
• G06N 3/08 - Learning methods
• G06N 3/09 - Supervised learning
• G06N 3/0895 - Weakly supervised learning, e.g. semi-supervised or self-supervised learning
• G06N 3/091 - Active learning
• G06N 3/092 - Reinforcement learning
• G06N 3/094 - Adversarial learning
• G06N 3/098 - Distributed learning, e.g. federated learning
• G06N 3/0985 - Hyperparameter optimisationMeta-learningLearning-to-learn

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining to apply a processing chain of post-processing filters (PPFs) to visual media data by: obtaining a list of cropped decoded pictures in output order, choosing the processing chain, applying each PPF in the processing chain to each cropped decoded picture in the list, and replacing cropped decoded pictures in the list with processed pictures. A conversion is performed between a visual media data and a bitstream based on the processing chain.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/635 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding using sub-band based transform, e.g. wavelets characterised by filter definition or implementation details
• H04N 19/80 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
• H04N 19/187 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a scalable video layer

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining to obtain a list of output pictures from a processing chain, wherein the list of output pictures can include more pictures than are output by a last post-processing filter (PPF) in the processing chain. The PPFs may be neural-network post-filter (NNPFs). A conversion is performed between a visual media data and a bitstream based on the processing chain.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/635 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding using sub-band based transform, e.g. wavelets characterised by filter definition or implementation details
• H04N 19/80 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
• H04N 19/187 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a scalable video layer

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: generating, for a conversion between a video unit of a video and a bitstream of the video, a prediction for the video unit by applying affine motion compensation, wherein the video unit is coded with geometric partitioning mode (GPM) mode; applying an overlapped block motion compensation (OBMC) to the prediction; and performing the conversion based on the prediction.

IPC Classes  ?

• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/119 - Adaptive subdivision aspects e.g. subdivision of a picture into rectangular or non-rectangular coding blocks
• H04N 19/169 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
• H04N 19/103 - Selection of coding mode or of prediction mode
• H04N 19/136 - Incoming video signal characteristics or properties
• H04N 19/60 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
• H04N 19/44 - Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder

Abstract

Embodiments of the present disclosure provide a solution for visual data transcoding. A method for visual data transcoding is proposed. The method comprises: reconstructing visual data from a first bitstream of the visual data; and encoding the reconstructed visual data into a second bitstream of the visual data, at least one of the reconstructing or the encoding being performed with a neural network (NN)-based model.

IPC Classes  ?

• H04N 19/10 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
• G06T 3/4046 - Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
• G06N 3/02 - Neural networks
• H04N 19/42 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation

Abstract

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: determining whether a first coding mode is enabled for a conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model, the visual data being at least a part of a picture of a video or an image; and performing the conversion based on the determining, wherein in the first coding mode, a set of residual samples associated with the visual data is partitioned into a plurality of subsets of residual samples, and a subset of residual samples among the plurality of subsets of residual samples is coded before a further subset of residual samples among the plurality of subsets of residual samples.

IPC Classes  ?

• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/172 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/60 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
• H04N 19/42 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation

Abstract

A mechanism for processing video data is disclosed. The mechanism determines to use only a slice-level filtering mode to indicate whether a block-level parameter selection is used. That is, a residual scaling flag is not used to indicate whether the block-level parameter selection is used. A conversion is performed between a visual media data and a bitstream based on the slice-level filtering mode.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/172 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
• G06N 3/0464 - Convolutional networks [CNN, ConvNet]
• H04N 19/82 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop
• H04N 19/136 - Incoming video signal characteristics or properties

Abstract

A mechanism for processing video data is disclosed. The mechanism determines to process video information with a high operation point (HOP) filter that includes a depth-wise convolutional layer or a group convolutional layer. A conversion is performed between a visual media data and a bitstream based on the HOP filter.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/80 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
• H04N 19/174 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a slice, e.g. a line of blocks or a group of blocks
• G06N 3/02 - Neural networks
• G06N 20/00 - Machine learning
• G06T 1/00 - General purpose image data processing

Abstract

A mechanism for processing video data is disclosed herein. The mechanism includes determining to apply a multiview monochrome sixteen-bit (Multiview Monochrome 16) profile to a visual media data. A conversion can then be performed between a visual media data and a bitstream based on the Multiview Monochrome 16 profile.

IPC Classes  ?

• H04N 19/597 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding specially adapted for multi-view video sequence encoding
• H04N 13/00 - Stereoscopic video systemsMulti-view video systemsDetails thereof
• H04N 21/236 - Assembling of a multiplex stream, e.g. transport stream, by combining a video stream with other content or additional data, e.g. inserting a URL [Uniform Resource Locator ] into a video stream, multiplexing software data into a video streamRemultiplexing of multiplex streamsInsertion of stuffing bits into the multiplex stream, e.g. to obtain a constant bit-rateAssembling of a packetised elementary stream
• H04N 19/00 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. In a method, for a conversion between a current video block of a video and a bitstream of the video, a first guiding vector associated with the current video block is determined. The first guiding vector comprises a first guiding block vector (BV) or a first guiding motion vector (MV). A first reference vector of a first reference block located based on the first guiding vector is determined. The first reference vector comprises a first reference block vector or a first reference motion vector. A vector prediction of the current video block is determined at least based on the first guiding vector and the first reference vector. The vector prediction comprises a block vector prediction or a motion vector prediction.The conversion is performed based on the vector prediction.

IPC Classes  ?

• H04N 19/50 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current block of a video and a bitstream of the video, that an input of a cross-component prediction (CCP) model comprises at least one of: a sample within a reference area, or a sample within the current block; and performing the conversion based on the CCP model.

IPC Classes  ?

• H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a video unit of a video and a bitstream of the video, that a cross-component prediction (CCP) model candidate is inserted to a CCP candidate list; and performing the conversion based on the CCP model candidate.

IPC Classes  ?

• H04N 19/44 - Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining to apply slice quantization parameters (QPs) as one or more extra inputs to a neural network (NN)-based super resolution (SR) process. A conversion is performed between a visual media data and a bitstream based on the NN-based SR process.

IPC Classes  ?

• G06T 3/40 - Scaling of whole images or parts thereof, e.g. expanding or contracting
• G06N 3/08 - Learning methods
• H04N 19/117 - Filters, e.g. for pre-processing or post-processing

Abstract

A mechanism for processing video data is disclosed. The mechanism includes determining that an adaptive coefficient precision for an adaptive loop filter (ALF) is set to a number M, where the number M is different from a fixed number used at an encoder or a decoder for the adaptive coefficient precision for the ALF. A conversion can then be performed between a visual media data and a bitstream based on the adaptive coefficient precision for the ALF set to the number M.

IPC Classes  ?

• H04N 19/82 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: obtaining, for a conversion between a video unit of a video and a bitstream of the video, a feature vector by applying a pre-analysis to a list of frames associated with the video unit; determining a prediction structure by feeding the feature vector to a model as an input; and performing the conversion based on the prediction structure.

IPC Classes  ?

• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current video block of a video and a bitstream of the video, prediction samples of the current video block based on an intra prediction mode and first information regarding whether to apply a bilateral filter to a set of reference samples of the current video block that is used for the intra prediction mode; and performing the conversion based on the prediction samples.

IPC Classes  ?

• H04N 19/593 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving spatial prediction techniques
• H04N 19/117 - Filters, e.g. for pre-processing or post-processing

Abstract

Embodiments of the present disclosure provide a method for point cloud coding. In the method, for a conversion between a current frame of a point cloud sequence and a bitstream of the point cloud sequence, a first trisoup node in a first slice of the current frame and a second trisoup node in a second slice of the current frame are determined. The first and second trisoup nodes are aligned based on a trisoup node size. The conversion is performed based on the aligned first and second trisoup nodes.

IPC Classes  ?

• G06T 9/40 - Tree coding, e.g. quadtree, octree

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. In a method, for a conversion between a current video block of a video and a bitstream of the video, a guiding block vector (BV) is determined based on a first BV shift of the current video block. A subblock-based block vector guided block vector prediction (SbBVGBVP) of the current video block is determined based on the guiding BV. The conversion is performed based on the SbBVGBVP.

IPC Classes  ?

• H04N 19/137 - Motion inside a coding unit, e.g. average field, frame or block difference
• H04N 19/124 - Quantisation

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current video block of a video and a bitstream of the video, prediction samples of the current video block based on an intra prediction mode and first information regarding whether to apply a deblocking filter to a set of reference samples of the current video block that is used for the intra prediction mode; and performing the conversion based on the prediction samples.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing

Abstract

Embodiments of the disclosure provide a solution for video processing. A method for video processing is proposed. The method includes: generating, for a conversion between a video unit of a video and a bitstream of the video, a prediction for the video unit by applying affine motion compensation, wherein the video unit is coded with geometric partitioning mode (GPM) mode; applying an overlapped block motion compensation (OBMC) to the prediction; and performing the conversion based on the prediction.

IPC Classes  ?

• H04N 19/583 - Motion compensation with overlapping blocks
• H04N 19/172 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
• H04N 19/159 - Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction
• H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: performing a conversion between a current video unit of a video and a bitstream of the video, wherein the bitstream comprises a first indication indicating first information regarding a usage of a neural network (NN) based filter for the current video unit, and the NN-based filter is configured to be used with one of a set of modes for the NN-based filter.

IPC Classes  ?

• G06T 9/00 - Image coding
• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• G06N 3/00 - Computing arrangements based on biological models
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: applying, for a conversion between a current video unit in a current picture of a video and a bitstream of the video, a neural network (NN) based filter on the current video unit; and performing the conversion based on the applying, wherein a size of a first input to the NN-based filter is larger than a size of the current video unit, and if the first input comprises a first set of samples outside the current picture, values of the first set of samples are determined based on a first padding scheme.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/82 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop
• G06N 3/02 - Neural networks

Abstract

A mechanism for processing video data is disclosed herein. The mechanism includes determining to apply a multiview ten-bit (Multiview 10) profile to a visual media data. A conversion can then be performed between a visual media data and a bitstream based on the Multiview 10 profile. Various constraints can also be applied to bitstreams conforming to the Multiview 10 profile or layers thereof.

IPC Classes  ?

• H04N 13/00 - Stereoscopic video systemsMulti-view video systemsDetails thereof
• H04N 19/597 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding specially adapted for multi-view video sequence encoding
• G06T 7/40 - Analysis of texture
• G06T 7/50 - Depth or shape recovery
• G06T 11/00 - 2D [Two Dimensional] image generation
• H04N 13/128 - Adjusting depth or disparity

Abstract

A mechanism for processing video data is disclosed. The mechanism determining that a current layer in a sub-bitstream (subBitstream) conforms to a multiview format range extension profile, wherein all active sequence parameter sets (SPSs) for the current layer and a reference layer of the current layer shall include a chroma format identification code (chroma_format_idc) equal to 0 only. A conversion is performed between a visual media data and a bitstream based on the multiview format range extension profile.

IPC Classes  ?

• H04N 19/597 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding specially adapted for multi-view video sequence encoding
• H04N 19/463 - Embedding additional information in the video signal during the compression process by compressing encoding parameters before transmission
• H04N 19/20 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using video object coding
• H04N 19/44 - Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder

Abstract

A mechanism for processing video data is disclosed. The mechanism determining that a layer conforms to a Multiview Extended profile, which may also be referred to as an Extended Multiview Main profile. A conversion is performed between a visual media data and a bitstream based on the Multiview Extended profile.

IPC Classes  ?

• H04N 19/597 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding specially adapted for multi-view video sequence encoding
• H04N 19/463 - Embedding additional information in the video signal during the compression process by compressing encoding parameters before transmission
• H04N 19/20 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using video object coding
• H04N 19/44 - Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current video block of a video and a bitstream of the video, whether to adjust a reconstructed reordered intra block copy (RRIBC) coded history-based motion vector prediction (HMVP) candidate of the current video block; and performing the conversion based on the determining.

IPC Classes  ?

• H04N 19/52 - Processing of motion vectors by encoding by predictive encoding
• H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
• H04N 19/159 - Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

A method for processing video data includes using one or more extended taps in an ALF or a CCALF and performing a conversion between a visual media data and a bitstream based on the extended taps used in the ALF. A syntax element structure in the bitstream contains one or more filters with at least one extended tap. A first syntax element is in the bitstream to indicate whether a filter with at least one extended tap is enabled.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/136 - Incoming video signal characteristics or properties
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. In the method, for a conversion between a current video block of a video and a bitstream of the video, temporal layer information of a video region associated with the current video block is determined. The temporal layer information indicates at least one of: a temporal layer, or a temporal layer index (Tid). A usage of subblock-based temporal motion vector prediction (SbTMVP) is determined based on the temporal information. The conversion is performed based on the usage of SbTMVP.

IPC Classes  ?

• H04N 19/109 - Selection of coding mode or of prediction mode among a plurality of temporal predictive coding modes

Abstract

Embodiments of the present disclosure provide a solution for video processing. In a method for video processing, for a conversion between a current video block of a video and a bitstream of the video, a value of a first variable of a merge candidate of the current video block is determined. Adjustment information of the first variable is determined based on at least one of: a template size, a sequence resolution, or a block size. The adjustment information comprises at least one of: whether to adjust the value of the first variable, or how to adjust the value of the first variable. The conversion is performed based on the adjustment information.

IPC Classes  ?

• H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component

Abstract

A mechanism for processing visual media data is disclosed. An extended dependent random access point (EDRAP) sample is determined. The EDRAP sample is a sample for which all subsequent samples in both decoding and output order can be correctly decoded provided that required preceding streaming access point (SAP) or EDRAP samples are available for referencing when decoding the EDRAP sample and the subsequent samples. A conversion is performed between a visual media data and a media data file based on the EDRAP sample.

IPC Classes  ?

• H04N 19/132 - Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: generating, based on a neighboring block of a current block of a video for a conversion between the current block and a bitstream of the video, a motion candidate list for an intra block copy template matching merge (IBC-TM-MERGE) mode for coding the current block, the neighboring block being coded with a reconstruction-reordered intra block copy (RRIBC) mode; and performing the conversion based on the motion candidate list.

IPC Classes  ?

• H04N 19/52 - Processing of motion vectors by encoding by predictive encoding
• G06V 10/75 - Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video featuresCoarse-fine approaches, e.g. multi-scale approachesImage or video pattern matchingProximity measures in feature spaces using context analysisSelection of dictionaries
• H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
• H04N 19/159 - Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

Examples of video encoding methods and apparatus and video decoding methods and apparatus are described. An example method of video processing includes performing a conversion between a video including multiple layers and a bitstream of the video according to a rule, wherein the rule specifies that, in a first process of sub-bitstream extraction to output a first output sub-bitstream, the first output sub-bitstream is extracted without removing network abstraction layer (NAL) units of a particular type and having a particular NAL unit header identifier value, and wherein the particular type includes an access unit delimiter (AUD) NAL unit.

IPC Classes  ?

• H04N 19/169 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
• H04N 19/172 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
• H04N 19/31 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using hierarchical techniques, e.g. scalability in the temporal domain
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a video unit of a video and a bitstream of the video unit, whether a template based processing is applied to the video unit, wherein the template based processing is based on at least one template in at least one of: a current picture or a reference picture of the video unit; and performing the conversion based on the determining.

IPC Classes  ?

• H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• H04N 19/172 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current block of a video and a bitstream of the video, that a component of the current block is coded with a coding mode and another component of the current block is coded with another coding mode; and performing the conversion based on the coding modes.

IPC Classes  ?

• H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. In the method, for a conversion between a current video block of a video and a bitstream of the video, at least one template segment of a current template of the current video block is determined. A reference template of the current video block is determined based on at least one motion information of the at least one template segment. The conversion is performed based on the reference template.

IPC Classes  ?

• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/577 - Motion compensation with bidirectional frame interpolation, i.e. using B-pictures
• H04N 19/513 - Processing of motion vectors

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. In the method, for a conversion between a current video block of a video and a bitstream of the video, information regarding applying a subblock-boundary based deblocking or filtering process to the current video block is determined based on a slice type. The conversion is performed based on the information. The information indicates at least one of: whether a kind of subblock-boundary based deblocking or filtering process is applied, or how the kind of subblock-boundary based deblocking or filtering process is applied.

IPC Classes  ?

• H04N 19/615 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding in combination with predictive coding using motion compensated temporal filtering [MCTF]
• H04N 19/50 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding

Abstract

Embodiments of the present disclosure provide a solution for video processing. In a method for video processing, for a conversion between a current video block of a video and a bitstream of the video, a value of a first variable of a merge candidate of the current video block is determined. Adjustment information of the first variable is determined based on at least one of: a template size, a block size or at least one threshold size. The adjustment information comprises at least one of: whether to adjust the value of the first variable, or how to adjust the value of the first variable. The conversion is performed based on the adjustment information.

IPC Classes  ?

• H04N 19/52 - Processing of motion vectors by encoding by predictive encoding

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current block of a video and a bitstream of the video, a cross-component prediction (CCP) model based on at least one of: a reference area related to the current block or a reference sample related to the current block; and performing the conversion based on the CCP model.

IPC Classes  ?

• H04N 19/61 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding in combination with predictive coding

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a video unit of a video and a bitstream of the video, affine information used in the video unit, wherein the video unit is not an affine-merge coded block or affine-advanced motion vector prediction (AMVP) coded block; storing the affine information used in the video unit; and performing the conversion based on the stored affine information.

IPC Classes  ?

• H04N 19/577 - Motion compensation with bidirectional frame interpolation, i.e. using B-pictures
• H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
• H04N 19/157 - Assigned coding mode, i.e. the coding mode being predefined or preselected to be further used for selection of another element or parameter
• H04N 19/52 - Processing of motion vectors by encoding by predictive encoding
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/44 - Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: applying, for a conversion between a current video block of a video and a bitstream of the video, a bi-directional optical flow (BDOF) process on the current video block, an optical flow derivation equation for the BDOF process being adjusted with at least one offset item; and performing the conversion based on the applying.

IPC Classes  ?

• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
• H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
• H04N 19/577 - Motion compensation with bidirectional frame interpolation, i.e. using B-pictures
• H04N 19/52 - Processing of motion vectors by encoding by predictive encoding

Abstract

Embodiments of the present disclosure provide a solution for point cloud processing. A method for point cloud processing is proposed. The method comprises: obtaining, for a conversion between a current point cloud (PC) sample of a point cloud sequence and a bitstream of the point cloud sequence, a first set of points in the current PC sample, the first set of points representing low frequency information of the current PC sample;and performing the conversion based on the first set of points.

IPC Classes  ?

• H04N 19/132 - Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a video unit of a video and a bitstream of the video, a parameter of a cross-component model for the video unit based on at least one of: a reference area related to the video unit or a previous cross-component model, wherein the cross-component model is a cross-component prediction (CCP) model or an inter convolutional cross-component model (CCCM); and performing the conversion based on the parameter of the cross-component model.

IPC Classes  ?

• H04N 19/159 - Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a video unit of a video and a bitstream of the video unit, whether an adaptive reordering-based motion compensation (ARMC) is applied to a prediction list of the video unit, wherein the prediction list comprises at least one a reconstruction reordered intra block copy (RRIBC) coded motion candidate; and performing the conversion based on the determining.

IPC Classes  ?

• H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/513 - Processing of motion vectors

Abstract

Embodiments of the disclosure provide a solution for video processing. A method for video processing is proposed. The method includes: determining, during a conversion between a video unit of a video and a bitstream of the video unit, a set of coding tree units (CTUs) included in an intra block copy (IBC) buffer or an IBC reference area of the video unit based on a current CTU, the video unit being applied with an IBC mode; and performing the conversion based on the set of CTUs.

IPC Classes  ?

• H04N 19/96 - Tree coding, e.g. quad-tree coding
• H04N 19/159 - Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: selecting, for a conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model, a synthesis transform from a plurality of synthesis transforms in the NN-based model, the plurality of synthesis transforms being configured for processing a reconstructed latent representation of the visual data that is derived from a same bitstream; and performing the conversion based on the selected synthesis transform.

IPC Classes  ?

• H04N 19/42 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards

Abstract

Systems, methods and apparatus for encoding, decoding or transcoding digital video are described. One example method of video processing includes performing a conversion between a video and a bitstream of the video including multiple layers, wherein the bitstream includes a plurality of supplemental enhancement information, SEI, messages associated with an access unit, AU, or a decoding unit, DU, of a particular output layer set, OLS, or a particular layer, wherein the plurality of SEI messages, including a message type different from scalable nesting type, is based on a format rule, and wherein the format rule specifies that each of the plurality of SEI messages has a same SEI payload content due to the plurality of SEI messages being associated with the AU or the DU of the particular OLS or the particular layer.

IPC Classes  ?

• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• C09K 13/06 - Etching, surface-brightening or pickling compositions containing an inorganic acid with organic material
• C23F 1/26 - Acidic compositions for etching refractory metals
• C23F 1/28 - Acidic compositions for etching iron group metals
• H01L 21/3213 - Physical or chemical etching of the layers, e.g. to produce a patterned layer from a pre-deposited extensive layer
• H04N 19/169 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
• H04N 19/46 - Embedding additional information in the video signal during the compression process

Abstract

Embodiments of the disclosure provide a solution for video processing. A method for video processing is proposed. The method includes: applying, during a conversion between a video unit of a video and a bitstream of the video, a signal process to the video unit based at least in part on a window-based attention module; and performing the conversion based on the processed video unit.

IPC Classes  ?

• H04N 19/167 - Position within a video image, e.g. region of interest [ROI]
• H04N 19/119 - Adaptive subdivision aspects e.g. subdivision of a picture into rectangular or non-rectangular coding blocks
• H04N 19/42 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation

Abstract

A video coding or decoding method includes using history-based motion vector prediction (HMVP) for conversion between multiple video blocks including a current block of video and a bitstream representation of the multiple video blocks such that for a uni-predicted block that for which a single reference picture is used for motion compensation, and refraining from updating a look-up table for HMVP candidates for the uni-predicted block. The video coding or decoding method further includes performing the conversion using look-up tables for the multiple video blocks.

IPC Classes  ?

• H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• H04N 19/109 - Selection of coding mode or of prediction mode among a plurality of temporal predictive coding modes
• H04N 19/159 - Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/513 - Processing of motion vectors
• H04N 19/52 - Processing of motion vectors by encoding by predictive encoding
• H04N 19/577 - Motion compensation with bidirectional frame interpolation, i.e. using B-pictures

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current block of a video and a bitstream of the video, that a first prediction mode is applied to the current block, deriving, in the first prediction mode, prediction samples of the current block based on reference values in a virtual buffer that are determined by a block vector for the current block; performing the conversion based on the prediction samples; determining a set of blocks from a plurality of blocks of the same video region based on coded information of the plurality of blocks, the plurality of blocks being coded before the current block; and updating the virtual buffer based on the set of blocks.

IPC Classes  ?

• H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
• H04N 19/159 - Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction
• H04N 19/167 - Position within a video image, e.g. region of interest [ROI]
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/96 - Tree coding, e.g. quad-tree coding

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: constructing a list of merge candidates for a target block of a video in a coding mode based on motion vector difference (MVD); reordering the list of merge candidates for the target block; and performing a conversion between the target block and a bitstream of the video based on the reordered list of merge candidates. Compared with the conventional solution, the proposed method can advantageously improve the coding efficiency.

IPC Classes  ?

• H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• H04N 19/159 - Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/52 - Processing of motion vectors by encoding by predictive encoding
• H04N 19/54 - Motion estimation other than block-based using feature points or meshes

Abstract

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: obtaining, for a conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model, at least one intermediate representation of the visual data in the NN-based model; applying a first filter in the NN-based model on the at least one intermediate representation, at least one parameter of the first filter being configured based on a format of output visual data from the conversion, the format indicating a relationship between a size of a first component of the output visual data and a size of a second component of the output visual data; and performing the conversion based on the applying.

IPC Classes  ?

• G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Abstract

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: obtaining, for a conversion between visual data and a bitstream of the visual data with a neural network (NN) -based model, a format for coding the visual data, the format indicating a relationship between a size of a first component of the coded visual data and a size of a second component of the coded visual data, and a first synthesis transform in the NN-based model being used for the first component; determining, based on the format, a second synthesis transform in the NN-based model that is used for the second component; and performing the conversion based on the first synthesis transform and the second synthesis transform.

IPC Classes  ?

• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. In the method, for a conversion between a current video block of a video and a bitstream of the video, a first prediction of the current video block is determined based on a first coding tool. The first coding tool compriss a subblock-based coding tool. A third prediction of the current video block is determined based on the first prediction and a second prediction of the current video block, the second prediction being determined based on a second coding tool different from the first coding tool. The conversion is performed based on the third prediction.

IPC Classes  ?

• H04N 19/513 - Processing of motion vectors
• H04N 19/103 - Selection of coding mode or of prediction mode

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method of processing video data is proposed. The method comprises: during a conversion between a current video block of a video and a bitstream of the video, obtaining a geometric partitioning mode (GPM) block associated with the current video block; and performing the conversion based on a motion-compensated prediction sample refinement process applied to the GPM block. Compared with the conventional solution, the proposed solution advantageously improves coding efficiency and compression ratios.

IPC Classes  ?

• H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a video unit of a video and a bitstream of the video, whether to use at least one of: a real-time calculated model or a derived model, based on a decoder derived approach; and performing the conversion based on the at least one of: the real-time calculated model or the derived model.

IPC Classes  ?

• H04N 19/159 - Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction

Abstract

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: applying, for a conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model, a first filter in the NN-based model on an output of a synthesis transform in the NN-based model, at least one parameter of the first filter being configured based on one or more of the following: a first format for coding the visual data, the first format indicating a relationship between a size of a first component of the coded visual data and a size of a second component of the coded visual data, or a second format of output visual data from the conversion; and performing the conversion based on the applying.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/172 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
• H04N 19/59 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving spatial sub-sampling or interpolation, e.g. alteration of picture size or resolution
• G06N 3/02 - Neural networks
• G06N 3/04 - Architecture, e.g. interconnection topology

Abstract

A mechanism for processing video data is disclosed. A type for a value taken by a region identifier (ID) in a region identifier (ID) type field (region_id_type) is determined. The type for the value taken by the region ID is coded in the region ID type field using four or less bits. A conversion between the visual media data and a media data file is performed based on the type for the value taken by the region ID in the region ID type field.

IPC Classes  ?

• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/136 - Incoming video signal characteristics or properties
• H04N 19/169 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding

Abstract

A video processing method is provided to include performing a conversion between a coded representation of a video including one or more video regions and the video. The coded representation includes side information applicable for in-loop reshaping (ILR) of some of the one or more video regions. The side information provides parameters for a reconstruction of a video unit of a video region based on a representation of the video unit in a first domain and a second domain and/or scaling chroma residue of a chroma video unit. The side information applicable to the some of the one or more video regions is coded without directly inheriting from other video regions.

IPC Classes  ?

• H04N 19/46 - Embedding additional information in the video signal during the compression process
• H04N 19/132 - Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
• H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component
• H04N 19/30 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using hierarchical techniques, e.g. scalability
• H04N 19/31 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using hierarchical techniques, e.g. scalability in the temporal domain
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/82 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: applying, for a conversion between a video unit of a video and a bitstream of the video, a cross-component prediction (CCP) mode to the video unit, based on decoding information;and performing the conversion based on the CCP mode.

IPC Classes  ?

• H04N 19/103 - Selection of coding mode or of prediction mode

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: deriving, for a conversion between a video unit of a video and a bitstream of the video, a cross-component prediction (CCP) model of a current block of the video unit, based on a previous CCP model coded block; and performing the conversion based on the CCP model.

IPC Classes  ?

• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component

Abstract

A mechanism for processing video data is disclosed. A filter is applied to a video unit. The filter employs an extended tap for a first sample in the video unit and a spatial tap for a second sample in the video unit. A conversion is performed between a visual media data and a bitstream based on the video unit.

IPC Classes  ?

• H04N 19/82 - Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop
• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
• H04N 19/96 - Tree coding, e.g. quad-tree coding

Abstract

A mechanism for processing video data is disclosed. One or more extended taps are determined for use in an adaptive loop filter (ALF). A conversion is performed between a visual media data and a bitstream based on the extended tap in the ALF. The extended tap may receive input data from different pictures than the current picture and/or from outside the spatial domain.

IPC Classes  ?

• H04N 19/117 - Filters, e.g. for pre-processing or post-processing
• H04N 19/167 - Position within a video image, e.g. region of interest [ROI]
• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• H04N 19/184 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
• H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current video block of a video and a bitstream of the video, that a first prediction mode is applied to the current block, reordering, in the first prediction mode, at least a first set of block vector difference (BVD) candidates of multiple BVD candidates corresponding to a first base candidate according to at least one criterion; deriving, based on the reordered BVD candidates, a block vector for the current video block; and performing the conversion based on the motion information.

IPC Classes  ?

• H04N 19/513 - Processing of motion vectors
• H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
• H04N 19/196 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the adaptation method, adaptation tool or adaptation type used for the adaptive coding being specially adapted for the computation of encoding parameters, e.g. by averaging previously computed encoding parameters
• H04N 19/58 - Motion compensation with long-term prediction, i.e. the reference frame for a current frame not being the temporally closest one

Abstract

Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. In the method, for a conversion between a current video block of a video and a bitstream of the video, an interweaved affine prediction and a bi-directional optical flow (BDOF) is applied for the current video block. The conversion is performed based on the applying.

IPC Classes  ?

• H04N 19/176 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock