Abstract: In a method and apparatus for video coding using Low-Frequency Non-Separable Transform (LFNST) mode, a coding unit (CU) is partitioned into one or more transform blocks (TBs). A syntax is determined at an encoder side or at a decoder side, where the determining step is performed by signaling the syntax at the encoder side or by parsing the syntax at the decoder side if one or more conditions are satisfied. The syntax indicates whether the LFNST mode is applied to the current CU and/or which LFNST kernel is applied when the LFNSF is applied, and the conditions comprise a target condition corresponding to that all target TBs in a target TB set have a TS mode indication as false, and the target TB set is selected from the TBs in the current CU. The current CU is encoded or decoded according to the LFNST mode.

Abstract: Disclosed is an image decoding method according to an embodiment, the image decoding method including: obtaining a first reference block and a second reference block, for bi-directional prediction of a current block; obtaining, from a bitstream, weight information for combining the first reference block with the second reference block; performing entropy decoding on the weight information to obtain a weight index; combining the first reference block with the second reference block according to a candidate value indicated by the weight index among candidate values included in a weight candidate group; and reconstructing the current block based on a result of the combining, wherein a first binary value corresponding to the weight index is entropy-decoded based on a context model, and the remaining binary value corresponding to the weight index is entropy-decoded by a bypass method.

Abstract: Disclosed is an image decoding method according to an embodiment, the image decoding method including: obtaining a first reference block and a second reference block, for bi-directional prediction of a current block; obtaining, from a bitstream, weight information for combining the first reference block with the second reference block; performing entropy decoding on the weight information to obtain a weight index; combining the first reference block with the second reference block according to a candidate value indicated by the weight index among candidate values included in a weight candidate group; and reconstructing the current block based on a result of the combining, wherein a first binary value corresponding to the weight index is entropy-decoded based on a context model, and the remaining binary value corresponding to the weight index is entropy-decoded by a bypass method.

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 and a bitstream of the video, wherein the bitstream includes network abstraction layer (NAL) units for multiple video layers according to a rule; wherein the rule defines a sub-bitstream extraction process by which NAL units are removed from the bitstream to generate an output bitstream, and wherein the rule specifies to remove all supplemental enhancement information (SEI) NAL units that contain a non-scalable-nested SEI message with a particular payload type, responsive to a list of NAL unit header layer identifier values in an output layer set (OLS) with a target OLS index not including all values of NAL unit header layer identifiers in all video coding layer (VCL) NAL units in the bitstream that is input to the sub-bitstream extraction process.

Abstract: The present disclosure provides methods and apparatuses for processing chroma sampled pictures. An exemplary video processing method includes: determining whether a chroma component is included in a sequence of frames; and in response to a determination that the chroma component is included in the sequence, activating a sub-process for processing the sequence, wherein the sub-process comprises one or more of joint coding for chroma residues (JCCR), block differential pulse coded modulation (BDPCM), palette mode, or adaptive color transform (ACT).

Abstract: Methods of selectively applying Bi-directional Optical Flow (BDOF) and Decoder-side Motion Vector Refinement (DMVR) on inter mode coded blocks employed in video coding standards, such as the now-current Versatile Video Coding (VVC) design, are performed at a computing device. In one method, when a current block is eligible for both applications of DMVR and BDOF based on a plurality of pre-defined conditions, the computing device uses a pre-defined criterion to classify the current block and then uses the classification in applying either BDOF or DMVR, but not both, on the block.

Abstract: An electronic apparatus performs a method of decoding video data. The method comprises: receiving the video signal that includes a first component and a second component; receiving a plurality of offsets associated with the second component; utilizing a characteristic measurement of the first component to obtain a classification category associated with the second component; selecting an offset from the plurality of offsets for the second component according to the classification category; and modifying the second component based on the selected offset. In some embodiments, the first component is a luma video component and the second component is a chroma video component.

Abstract: Disclosed is an image decoding method according to an embodiment, the image decoding method including: obtaining a first reference block and a second reference block, for bi-directional prediction of a current block; obtaining, from a bitstream, weight information for combining the first reference block with the second reference block; performing entropy decoding on the weight information to obtain a weight index; combining the first reference block with the second reference block according to a candidate value indicated by the weight index among candidate values included in a weight candidate group; and reconstructing the current block based on a result of the combining, wherein a first binary value corresponding to the weight index is entropy-decoded based on a context model, and the remaining binary value corresponding to the weight index is entropy-decoded by a bypass method.

Abstract: A three-dimensional data encoding method includes: generating frame data items by encoding point cloud data items of frames; and generating a bitstream including the frame data items. Each of the frame data items includes processing unit data items corresponding to processing units obtained by dividing one frame. Each of the processing unit data items includes a frame identifier indicating a frame to which the processing unit data item belongs and a processing unit identifier indicating a processing unit corresponding to the processing unit data item. Values of the frame identifiers corresponding to the frame data items placed in the bitstream are set in a predetermined order, and values of the processing unit identifiers corresponding to the processing unit data items placed in the frame data item are set in an arbitrary order.

Abstract: An image component prediction method, an encoder, and a computer storage medium are provided. The method includes: encoding chroma components in a colour component encoding process; and acquiring a prediction value of a luma component according to the encoded chroma components.

Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform obtaining video data, parsing a video parameter set (VPS) syntax of the video data, determining whether a value of a syntax element of the VPS syntax indicates a picture order count (POC) value of an access unit (AU) of the video data, and setting at least one of a plurality of pictures, slices, and tiles of the video data to the AU based on the value of the syntax element.

Abstract: Implementations of the present disclosure provide a solution for reordering merge candidates. In this solution, during a conversion between a current video block of a video and a bitstream of the video, a template matching cost associated with each of a plurality of candidates of motion information for the current video block is determined. The template matching cost is determined based on a first difference between a set of neighboring samples of the current video block and a set of reference samples corresponding to the set of neighboring samples, and a second difference between a set of reconstructed samples neighboring to the set of neighboring samples and the set of reference samples. The set of reference samples is determined based on motion information indicated by a respective candidate. Then, the plurality of candidates of motion information is reordered based on the template matching cost.

Abstract: A non-random-access video stream is received. A first image block is encoded after second image blocks according to a non-random-access processing order. View direction data is received to indicate a viewer's view direction coinciding with a location covered by the first image block. The first image block is encoded into the random-access video stream before the second image blocks in a random-access processing order. The random-access video stream is delivered to a recipient decoding device operated by the viewer to cause the first image block to be processed and rendered before the second image blocks according to the random-access processing order.

Abstract: Systems, methods, and non-transitory computer-readable media can identify a virtual character being presented to a user within a real-time immersive environment. A first animation to be applied to the virtual character is determined. A nonverbal communication animation to be applied to the virtual character simultaneously with the first animation is determined. The virtual character is animated in real-time based on the first animation and the nonverbal communication animation.

Abstract: Disclosed herein is a method for decoding a video including determining a coding unit to be decoded by block partitioning, decoding prediction syntaxes for the coding unit, the prediction syntaxes including a skip flag indicating whether the coding unit is encoded in a skip mode, after the decoding of the prediction syntaxes, decoding transform syntaxes including a transformation/quantization skip flag and a coding unit cbf, wherein the transformation/quantization skip flag indicates whether inverse transformation, inverse quantization, and at least part of in-loop filterings are skipped, and the coding unit cbf indicates whether all coefficients in a luma block and two chroma blocks constituting the coding unit are zero, and reconstructing the coding unit based on the prediction syntaxes and the transform syntaxes.

Abstract: Delay based on WPP processing is reduced. An image decoding apparatus (31) includes: a prediction image generation unit (308) by using decoded data from a first position to a second position, the first position being, in a CTU row immediately above a CTU row including a target CTU, identical to a position of the target CTU, the second position being a position one CTU forward relative to the first position; and an entropy decoding unit (301) that performs decoding of the target CTU by using the decoded data from the first position to the second position, the first position being, in the CTU row immediately above the CTU row including the target CTU, identical to the position of the target CTU, the second position being a position one CTU forward relative to the first position.

Abstract: According to a disclosure of the present document, scaling list data and scaling list-related information may be hierarchically signaled, and through same, the amount of data which must be signaled for video/image coding may be reduced, and coding efficiency may be increased.

Abstract: Disclosed is an image decoding method according to an embodiment, the image decoding method including: obtaining a first reference block and a second reference block, for bi-directional prediction of a current block; obtaining, from a bitstream, weight information for combining the first reference block with the second reference block; performing entropy decoding on the weight information to obtain a weight index; combining the first reference block with the second reference block according to a candidate value indicated by the weight index among candidate values included in a weight candidate group; and reconstructing the current block based on a result of the combining, wherein a first binary value corresponding to the weight index is entropy-decoded based on a context model, and the remaining binary value corresponding to the weight index is entropy-decoded by a bypass method.

Abstract: A decoder configuration method includes: acquiring at least two compatibility grade configurations for configuring decoding parameters of a decoder, the different compatibility grade configurations being different in priority level, decoding property and decoder compatibility; selecting one compatibility grade configuration from the compatibility grade configurations according to the priority levels from high to low; configuring the decoder according to the compatibility grade configuration; starting the decoder, and performing decoding abnormality detection processing on the decoder to obtain an abnormality detection result; and performing hardware decoding processing on a to-be-decoded video according to the compatibility grade configuration to obtain a decoding processing result based on the abnormality detection result indicating that the decoder is normal, and determining that the current compatibility grade configuration is applicable to the decoder according to the decoding processing result in respons

Abstract: A decoding method performed by a decoding apparatus, according to embodiments of the present document, may comprise the steps of: acquiring, via a bitstream, image information including residual information; generating reconstructed samples of a current picture on the basis of the residual information; and generating modified reconstructed samples by performing an in-loop filtering procedure on the reconstructed samples of the current picture, wherein whether or not the in-loop filtering procedure is performed across virtual boundaries is determined. The virtual boundaries can bring, to the decoding apparatus, advantages from a hardware perspective.

Abstract: An image decoding method is disclosed. The image decoding method includes obtaining intra prediction mode information of a current block from a bitstream, determining an intra prediction mode of the current block based on the intra prediction mode information and an intra prediction mode of a neighboring block located around the current block, deriving a value of a first filter flag for use of filtering of an intra prediction reference sample of the current block based on coding parameters for the current block, selecting an interpolation filter to be used for intra prediction of the current block based on the first filter flag, and generating an intra prediction block of the current block using the selected interpolation filter.

Abstract: A device may be configured to signal output layer set information according to one or more of the techniques described herein. The device comprising one or more processors configured to: receiving a video parameter set including syntax elements; parsing first syntax element from the video parameter set specifying whether at least one output layer set specified by the video parameter set contains more than one layer; and parsing second syntax element specifying whether the video parameter contains sequence-level hypothetical reference decoder parameters in a case that the first syntax element specifies that at least one output layer set specified by the video parameter set contains more than one layer.

Abstract: According to one embodiment of the present document, a (decoded) picture can be split into sub-pictures. Information related to the sub-pictures can be acquired by means of a decoding device, and a decoding procedure can be performed on the basis of the information related to the sub-pictures. In one embodiment, the decoding device can determine, on the basis of the information about the sub-pictures, the location in which information related to locations of virtual boundaries for in-loop filtering is signaled.

Abstract: Aspects of the disclosure provide a method and an apparatus including processing circuitry for video encoding. The processing circuitry determines a maximum number of geometric merge mode merge candidates, and generates maximum number of geometric merge mode candidates information based on a relation between the maximum number of geometric merge mode merge candidates and a maximum number of merge candidates. The processing circuitry generates a coded video bitstream including coding information. The coding information indicates that a geometric merge mode is enabled for a coding level higher than a picture level of a current picture and the maximum number of merge candidates satisfies a condition. The maximum number of geometric merge mode merge candidates is equal to the maximum number of merge candidates minus a value indicated by the maximum number of geometric merge mode candidates information.

Abstract: There is disclosed a method, an apparatus and a computer program product for video encoding and decoding. In accordance with an embodiment the method for encoding comprises concluding that a coded video sequence starts at particular position in a bitstream, wherein the coded video sequence is a sequence of coded pictures in decoding order that is independently decodable and is followed by another coded video sequence or the end of the bitstream, and wherein the bitstream comprises access units, and an access unit comprises coded video data for a single time instance and associated other data, and an access unit comprises one or more network abstraction layer (NAL) units; and indicating in an access unit delimiter to treat the NAL unit(s) associated with the access unit delimiter as a start of a coded video sequence.

Abstract: An image decoding method performed by a decoding device according to the present disclosure comprises the steps of: receiving a bitstream including prediction information for a current block; deriving a chroma array type for the current block on the basis of a separate color plane flag indicating whether three color components are separately coded and a chroma format index indicating a chroma format sampling structure for the current block, which are included in the prediction information for the current block; deriving prediction samples for the current block on the basis of the derived chroma array type; and deriving reconstructed samples for the current block on the basis of the prediction samples.

Abstract: Interaction between MV precisions and MV difference coding is described. In an exemplary aspect, a method for video processing includes determining, for a conversion between a first block of video and a bitstream representation of the first block, whether a symmetric motion vector difference (SMVD) mode for the first block is enabled or disabled and/or how to apply the SMVD mode for the first block, based on at least one of motion information, a motion vector difference (MVD) precision and a motion vector (MV) precision of the first block; and performing the conversion based on the determining.

Abstract: A method of video processing includes determining, for a conversion between a current block of a video and a bitstream representation of the video, an operation associated with a list of motion candidates based on a condition related to a characteristic of the current block. The list of motion candidates is constructed for a coding technique or based on information from previously processed blocks of the video. The method also includes performing the conversion based on the determining.

Abstract: A method and apparatus for performing a forward mapping function or its inverse is implemented through information conveyed in a bitstream to perform mapping. The information can be implemented in a uniform or non-uniform lookup table. A decoder can receive the information and derive the inverse function to be used. In one embodiment, a decoder receives information representative of an inverse mapping function and uses the information to implement an inverse mapping lookup table for intra coded picture portions and can derive a forward mapping lookup table to be used with an inverse mapping lookup table for inter coded picture portions.

Abstract: An image decoding method performed by a decoding device according to the present document comprises the steps of: obtaining, through a bitstream, image information including a motion information candidate index and residual information; deriving motion information of a current block on the basis of the motion information candidate index; deriving a prediction sample on the basis of the motion information; deriving, on the basis of residual syntax elements for a current residual coefficient in the current block, the current residual coefficient; deriving a residual sample on the basis of the current residual coefficient; and deriving a reconstruction sample of the current block on the basis of the prediction sample and the residual sample.

Abstract: A video coding mechanism is disclosed. The mechanism includes receiving a bitstream comprising an output layer set (OLS) and a video parameter set (VPS). The OLS includes one or more layers of coded pictures and the VPS includes an OLS mode identification code (ols_mode_idc) specifying that for each OLS, all layers in the each OLS are output layers. The output layers are determined based on the ols_mode_idc in the VPS. A coded picture from the output layers is decoded to produce a decoded picture. The decoded picture is forwarded for display as part of a decoded video sequence.

Abstract: A method and apparatus for adaptively processing video samples in a video signal frame, the video samples being arranged in a Largest Coding Unit. The method comprises extracting a plurality of video samples from the Largest Coding Unit, calculating a correction offset for a first video sample of the extracted plurality of video samples upon the basis of a first value of the first video sample and a second value of a second video sample of the extracted plurality of video samples, and weighting the first video sample with the correction offset.

Abstract: A video decoding method performed by a video decoding device according to this document comprises the steps of: parsing prediction weighted table syntax from a bitstream; parsing information on the number of reference pictures in a reference picture list from the prediction weighted table syntax; deriving weights for weighted prediction on the basis of the information on the number of reference pictures; deriving prediction samples of a current block by performing weighted prediction for the current block on the basis of the weights; and reconstructing a current picture on the basis of the prediction samples, wherein the prediction weighted table syntax may be parsed from a picture header of the bitstream.

Abstract: Provided is a video decoding method including: obtaining constrained prediction information indicating whether a constrained intra prediction mode is enabled; generating reconstructed samples of a current block by using prediction samples of the current block and residual samples of the current block; when the constrained intra prediction mode is enabled by the constrained prediction information and a prediction mode of a neighboring block is not an intra prediction mode, determining a padding value corresponding to a neighboring sample adjacent to outside of a boundary between the current block and the neighboring block, by using the reconstructed samples of the current block; and performing post-reconstruction filtering on the current block, by using the padding value corresponding to the neighboring sample.

Abstract: A method of filtering reconstructed video data including inputting a reconstructed luma picture sample array, setting a luma location corresponding to a current chroma sample to a location defined by a horizontal location in the chroma sample multiplied by a sub-width value and a vertical location in the chroma sample multiplied by a sub-height value, deriving luma sample locations inside the reconstructed luma picture sample array by using the luma location, and deriving a variable by using cross-component filter coefficients and the reconstructed luma picture sample array defined by at least one of the luma sample locations. The variable is modified by using a current chroma block of samples.

Abstract: An encoder includes circuitry and memory coupled to the circuitry. The circuitry: executes a second process of applying a second filter to the first image to generate a second image, not holding the second image as a reference image, holding the first image as a reference image, and displaying the second image; writes coefficients of each of one or more filter candidates that are candidates for the second filter into a bitstream, wherein the coefficients are included in a first storage location when written into the bitstream; and writes a parameter that specifies, for each image, one of the one or more filter candidates as the second filter into the bitstream, wherein the parameter is included in a second storage location when written into the bitstream, and the second storage location is different from the first storage location.

Abstract: A neural processor. In some embodiments, the processor includes a first tile, a second tile, a memory, and a bus. The bus may be connected to the memory, the first tile, and the second tile. The first tile may include: a first weight register, a second weight register, an activations buffer, a first multiplier, and a second multiplier. The activations buffer may be configured to include: a first queue connected to the first multiplier and a second queue connected to the second multiplier. The first queue may include a first register and a second register adjacent to the first register, the first register being an output register of the first queue. The first tile may be configured: in a first state: to multiply, in the first multiplier, a first weight by an activation from the output register of the first queue, and in a second state: to multiply, in the first multiplier, the first weight by an activation from the second register of the first queue.

Abstract: A video encoder may be configured to encode multiple adaptive loop filter sets in an adaptation parameter set associated with the video data. A video decoder may receive the multiple adaptive loop filter sets in the adaptation parameter set associated with video data, determine one or more adaptive loop filters from the multiple adaptive loop filter sets, and apply the determined one or more adaptive loop filters to the video data.

Abstract: A method of decoding a coding unit from a coding tree unit of an image frame from a video bitstream. The method comprises determining a scan pattern for a transform block, the scan pattern progressing from a current collection to a next collection of the plurality of collections after completing scanning of the current collection; decoding residual coefficients from the video bitstream according to the scan pattern; determining a multiple transform selection index for the coding unit, decoding the multiple transform selection index from the video bitstream if a last significant coefficient encountered along the scan pattern is at or within a threshold cartesian location of the transform block, and determining the multiple transform selection index to indicate that multiple transform selection is not used if the last significant residual coefficient position of the transform block along the scan pattern outside the threshold location; and transforming the decoded residual coefficients.

Abstract: An electronic apparatus performs a method of coding video data. The method comprises: receiving, from the bitstream, syntax elements associated with a coding unit, wherein the syntax elements include a first coded block flag (CBF) for residual samples of a first chroma component, a second CBF for residual samples of a second chroma component, and a third syntax element indicating whether adaptive color transform (ACT) is applied to the coding unit; determining whether to perform the chroma residual scaling to the residual samples of the chroma components according to the first CBF, the second CBF, and the third syntax element; in accordance with a determination to perform the chroma residual scaling to the residual samples of the first and second chroma components, scaling the residual samples of the at least one of the first and second chroma components based on a corresponding scaling parameter.

Abstract: According to the disclosure of the present document, an NAL unit type for slices in a picture may be determined on the basis of NAL unit type-related information relating to whether the picture has a mixed-NAL unit type, and a type mixed with another type of NAL unit as well as an IRAP for a picture having the mixed-NAL unit type may be provided.

Abstract: The present disclosure provides a computer-implemented method for encoding video. The method includes coding one or more first flags in a sequence parameter set (SPS) of a bitstream, and coding at least one second flag in the SPS if one or more coding modes are enabled for a video sequence associated with the SPS. The one or more first flags indicate whether the one or more coding modes are enabled for the video sequence. The at least one second flag indicates whether a multi-level control is activated for the one or more coding modes.

Abstract: An artificial intelligence (AI) encoding apparatus includes at least one processor configured to: determine a downscaling target, based on a target resolution for a first image, obtain the first image by AI-downscaling an original image using an AI-downscaling neural network corresponding to the downscaling target, generate image data by encoding the first image, select AI-upscaling neural network set identification information, based on the target resolution of the first image, characteristic information of the original image, and a target detail intensity, generate AI data including the target resolution of the first image, bit depth information of the first image, the AI-upscaling neural network set identification information, and encoding control information, and generate AI encoding data including the image data and the AI data; and a communication interface configured to transmit the AI encoding data to an AI decoding apparatus, wherein the AI data includes information about an AI-upscaling neural netwo

Abstract: A filter, to an encoder and a decoder using the filter, to a filtering method and a corresponding program, as well as to encoding and decoding using the filtering method or the filter. The method includes obtaining of an extended reconstructed block by extending the current reconstructed block to include at least padding samples from the current reconstructed block. After padding, a current pixel of the extended reconstructed block and its neighboring pixels are loaded into a linear buffer and transformed with a one-dimensional (1D) transform. The method is performed in frequency domain using a look-up table and the filtered pixels are transformed back.

Abstract: Disclosed is a video decoding method that decodes a bitstream, the method including receiving a picture parameter set (PPS) comprising at least one of first information indicating whether the same reference picture list is applied to slices comprised in a picture and second information indicating whether additional information on modification of the reference picture list is present, and deriving a construction of the reference picture list based on the PPS. Accordingly, there are provided a method and an apparatus for signaling by a picture whether the construction of the reference picture list is modified when constructing the reference picture list.

Abstract: Provided are a method for determining a prediction direction, a decoder and a computer storage medium. The method is implemented by a decoder. The method includes that: a Direct Mode (DM) in a chroma intra prediction mode of a block to be decoded is acquired (S101); and an index number of a prediction direction in a DM derived mode is determined based on an offset N and an index number M of a prediction direction in the DM to determine the DM derived mode (S102).

Abstract: This disclosure relates encoding and decoding of motion vector difference in for inter-predicting a video block. An example is disclosed for decoding an inter-predicted video block of a video stream. The method includes deriving an inter-prediction mode for the video block from the video stream; deriving a motion vector prediction mode for the video block; deriving, from the video stream, a context for signaling a set of syntax elements associated with a Motion Vector Difference (MVD) associated with the video block based on the inter-prediction mode and/or the motion vector prediction mode; and decoding the video block based on the set of syntax elements and the derived context.

Abstract: An encoder capable of properly handling an image to be encoded or decoded includes processing circuitry and memory connected to the processing circuitry. Using the memory, the processing circuitry: obtains parameters including at least one of (i) one or more parameters related to a first process for correcting distortion in an image captured with a wide angle lens and (ii) one or more parameters related to a second process for stitching a plurality of images; generates an encoded image by encoding a current image to be processed that is based on the image or the plurality of images; and writes the parameters into a bitstream including the encoded image.

Abstract: An encoder includes circuitry and memory coupled to the circuitry. In residual coding of a current block to which an orthogonal transform is not applied, when coefficient information flags relating to a coefficient in the current block are encoded, the circuitry: performs a level mapping process to transform the coefficient to a second coefficient by using a predicted value, in which the predicted value is determined based on neighboring coefficients of the coefficient within the current block; encodes second coefficient information flags by Context-based Adaptive Binary Arithmetic Coding (CABAC), each of the second coefficient information flags relating to the second coefficient; and encodes a remainder value of the coefficient with Golomb-Rice code, and when the coefficient information flags are not encoded, in operation, the circuitry: skips the level mapping process; and encodes a value of the coefficient with the Golomb-Rice code.

Abstract: According to the disclosure of the present disclosure, the index of an alternative filter is derived from ALF information, and an ALF procedure for a chroma component of a current block can be performed on the basis of the alternative filter.