Abstract: A computer system acquires a video bitstream. The video bitstream includes data associated with multiple encoded pictures. Each encoded picture includes one or more coding units (CUs). While decoding a current CU of a picture in the video bitstream, the current CU having a plurality of reference subblocks located in one or more reference pictures, in accordance with a determination that the plurality of reference subblocks satisfy a first set of predefined conditions for enabling a subblock-based temporal motion vector prediction (SbTMVP) mode, the computer system retrieves, from the video bitstream, syntax elements associated with the SbTMVP mode. The computer system then decodes the current CU using the retrieved syntax elements associated with the SbTMVP mode.

Abstract: A method and an apparatus for image filtering in video coding using a neural network are provided. The method includes: loading, a plurality of quantization parameter (QP) map (QpMap) values at a plurality of QpMap channels into the neural network; obtaining a QP scaling factor by adjusting a plurality of input QP values related to an input frame; and adjusting, according to a QP scaling factor, the plurality of QpMap values for the neural network to learn and filter the input frame to the neural network.

Abstract: A method for video decoding includes: obtaining a first control flag signaled at a specified level that includes one of following levels: a Transform Block (TB) level, a Coding Block (CB) level, a slice level, a picture level, or a sequence level, wherein the first control flag indicates whether a Decoder-side High Precision Intra Mode Derivation (DHI) mode is enabled, and in response to determining that the DHI mode is enabled, deriving, using a predefined method, high precision intra mode under a predefined condition, where the predefined condition includes one of following conditions: specific modes, or specific block sizes, or the DHI mode is used at the specified level.

Abstract: Implementations of the disclosure provide a video coding method and apparatus thereof. A decoding method includes: selecting, by a decoder, templates of neighboring samples for a video block; applying, by the decoder, a gradient filter window to the templates to calculate gradients for the respective templates; determining, by the decoder, a histogram of gradient based on the calculated gradients; selecting, by the decoder, a dominant gradient direction based on the histogram of gradient; and determining, by the decoder, an extrapolation direction for extrapolating neighboring samples of the video block based on the dominant gradient direction.

Abstract: Methods for video decoding and encoding, apparatuses and non-transitory storage media are provided. In one decoding method, the decoder obtains a geometric partition mode (GPM) blending area index at a certain level associated with a picture, where the GPM blending area index indicates a blending area width from a set of blending area widths. The decoder obtains one or more weighting values that are used to blend prediction samples of a GPM mode based on the blending area width indicated by the GPM blending area index. Furthermore, the decoder obtains a GPM predictor based on the one or more weighting values.

Abstract: An electronic apparatus performs a method of decoding video data. The method comprises: receiving, from a bitstream, a first control flag that indicates merge mode with motion vector difference (MMVD) is enabled for one or more coding units in a video sequence; receiving a first syntax from the video data that identifies a set of motion vector difference (MVD) offsets from a plurality sets of MVD offsets; receiving, a second control flag corresponding to a respective coding unit of the one or more coding units, which indicates the MMVD is applied to the coding unit; receiving a second syntax that selects an MVD offset from the identified set of MVD offsets, and a third syntax that selects an MVD direction; forming MVD based on the selected MVD offset and MVD direction; and reconstructing the coding unit by applying the formed MVD to generate motion vectors to the coding unit.

Abstract: Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for video decoding. In one method, a decoder constructs a plurality of intra prediction mode groups (IPMGs), and each IPMG of the plurality of IPMGs comprises a plurality of intra prediction modes; in response to determining that a current IPMG is indicated to generate an intra prediction mode for a current block, the decoder may derive a scheme of intra prediction modes to determine a best mode within the current IPMG to generate intra prediction samples for the current block, and the scheme of intra prediction modes comprises decoder-side intra mode derivation (DIMD) and template-based intra mode derivation (TIMD).

Abstract: Methods, apparatuses, and non-transitory computer-readable storage medium are provided for decoding video signals. A decoder receives a bitstream that includes a sequence parameter set (SPS) for video data. The decoder obtains arranged partition constraint syntax elements in sequence parameter set (SPS) level, and the arranged partition constraint syntax elements include intra prediction related syntax elements and inter prediction related syntax elements, and the arranged partition constraint syntax elements are arranged so that the intra prediction related syntax elements are defined before the inter prediction related syntax elements. The decoder decodes the video data based on the arranged partition constraint syntax elements.

Abstract: Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for decoding a video signal. A decoder partitions a video picture into a plurality of coding units (CUs) comprising a lossless CU. The decoder may further receive a high-level syntax. The high-level syntax may include, for example, a first flag that indicates whether a residual coding scheme is switchable.

Abstract: An electronic apparatus performs a method of decoding video data. The method comprises: receiving, from bitstream, a plurality of syntax elements associated with a coding unit, wherein the plurality of syntax elements indicate a size of the coding unit and a coding tree type of the coding unit; determining a minimum palette mode block size for the coding unit in accordance with the coding tree type of the coding unit; in accordance with a determination that the size of the coding unit is greater than the minimum palette mode block size: receiving, from the bitstream, a palette mode enable flag associated with the coding unit; and decoding, from the bitstream, the coding unit in accordance with the palette mode enable flag.

Abstract: The present disclosure provides a method for video decoding, comprising: obtaining a candidate list comprising block candidates, wherein the block candidates are reconstructed blocks in a same frame as a current block to be predicted; receiving an index indicating one of the block candidates as the selected block candidate; and predicting the sample values of the current block with filtered intra block copy (FIBC) mode in response to determining that the selected block candidate has been predicted with FIBC mode.

Abstract: Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for video encoding and decoding. An encoder may signal a control flag in a slice header level. The encoder may signal at least one syntax element in the slice header level. The control flag may be a residual coding disabled flag. The at least one syntax element may comprise a syntax element related to a residual coding rice index.

Abstract: An information processing device comprises a processor which, in a case in which an action of a user is detected within a predetermined period and second control information is included in recognition data of a speech signal acquired within the predetermined period, starts new control using the second control information as a parameter without recognizing a wake word. The predetermined period is a period during which a control is executed or a predetermined period after completion of the control. The control is related to processing based on the wake word and control information, the wake word and the control information being included in the recognition data derived from the acquired speech signal. The action is estimated based on the control.

Abstract: A method for video encoding, a method for video decoding, and apparatuses thereof are provided. RPR prediction samples may be determined for a video block from a video frame of a video based on one or more reference frames and motion information associated with the video block. At least one of the one or more reference frames has a resolution different from a resolution of the video frame. The RPR prediction samples may be filtered based on a template-based adaptive filter to generate filtered RPR prediction samples for the video block. A predictive block including the filtered RPR prediction samples may be determined for the video block.

Abstract: Implementations of the disclosure provide systems and methods for motion compensation prediction. The method may include obtaining a video block of a video frame from a bitstream. The method may further include performing a geometry partition on the video block to obtain a first partition and a second partition. The method may further include applying a first motion prediction mode to the first partition and a second motion prediction mode to the second partition. At least one of the first motion prediction mode or the second motion prediction mode is an affine motion prediction mode. The first motion prediction mode and the second motion prediction mode are a same coding mode with different parameters.

Abstract: An electronic apparatus performs a method of decoding video data. The method comprises: receiving, from a bitstream, a first control flag that indicates merge mode with motion vector difference (MMVD) is enabled for one or more coding units in a video sequence; receiving a first syntax from the video data that identifies a set of motion vector difference (MVD) offsets from a plurality sets of MVD offsets; receiving, a second control flag corresponding to a respective coding unit of the one or more coding units, which indicates the MMVD is applied to the coding unit; receiving a second syntax that selects an MVD offset from the identified set of MVD offsets, and a third syntax that selects an MVD direction; forming MVD based on the selected MVD offset and MVD direction; and reconstructing the coding unit by applying the formed MVD to generate motion vectors to the coding unit.

Abstract: Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for video coding. In one method, a decoder obtains, for a current chroma block, a non-linear model (non-LM) mode and a linear model (LM) mode, and the LM mode includes a cross component linear model (CCLM) mode and a multi-model linear model (MMLM) mode. The decoder then combines the non-LM mode and the LM mode for a multi-hypothesis-based chroma prediction (MCP) for the current chroma block.

Abstract: A method for video coding is provided. The method includes: receiving, by a decoder, a syntax element; and performing, by the decoder, a decoding process based on a value of the syntax element, wherein the syntax element specifies whether network abstraction layer (NAL) units of a picture have a same NAL unit type, and the value of the syntax element is equal to 0 when the picture is a gradual decoding refresh (GDR) picture or an intra random access point (IRAP) picture.

Abstract: An electronic apparatus performs a method of decoding video data, including: receiving, a plurality of frames, each including a first component and a second component; determining, for a first frame, one or more classifiers for the second component respectively from one or more samples of the first component associated with a respective sample of the second component; and when a received syntax element indicates that differential pulse-code modulation (DPCM) is enabled for signalling a first group of differential sample offsets for the second component of a second frame according to the one or more classifiers: determining a second group of sample offsets for the second component of the second frame by adding the first group of differential sample offsets of the second frame to a first group of sample offsets for the second component of the first frame according to the one or more classifiers.

Abstract: An electronic apparatus performs a method of decoding video data, including receiving, from bitstream, a first syntax element in a slice header of a slice that indicates whether luma mapping with chroma scaling (LMCS) is applied to a coding unit in the slice; receiving a second syntax element for the coding unit that indicates whether the coding unit has been coded using adaptive color-space transform (ACT); if the second syntax element has a non-zero value, decoding the coding unit by applying inverse ACT to convert luma and chroma residuals of the coding unit from a transformed color space to an original color space of the video data; and if the first syntax element has a non-zero value, decoding the coding unit by performing inverse luma mapping to the luma samples and inverse scaling to the chroma residuals of the coding unit after performing the inverse ACT.