Abstract: A method and apparatus for neural network based cross component prediction with low-bit precision during encoding or decoding of an image frame or a video sequence, which may include reconstructing a chroma component based on a received luma component using a pre-trained deep neural network (DNN) cross component prediction (CCP) model for chroma prediction, and updating a set of parameters of the pre-trained DNN CCP model with low-bit precision. The method may also include generating an updated DNN CCP model for chroma prediction with low-bit precision based on at least one video sequence, and using the updated DNN CCP model for cross component prediction of the at least one video sequence at reduced processing time.

Abstract: In the present disclosure, a method for compressing a feature map is provided, where the feature map is generated by passing a first input through a deep neural network (DNN). A respective optimal index order and a respective optimal unifying method are determined for each of super-blocks that are partitioned from the feature map. A selective structured unification (SSU) layer is subsequently determined based on the respective optimal index order and the respective optimal unifying method for each of the super-blocks. The SSU layer is added to the DNN to form an updated DNN, and is configured to perform unification operations on the feature map. Further, a first estimated output is determined, where the first estimated output is generated by passing the first input through the updated DNN.

Abstract: Aspects of the disclosure provide methods and apparatuses for point cloud compression and decompression. In some examples, an apparatus for point cloud compression/decompression includes processing circuitry. In some examples, the processing circuitry receives a bitstream carrying compressed data for a point cloud. The processing circuitry determines that a current node in an octree structure is eligible for an isolated mode. The octree structure corresponds to three dimensional (3D) partitions of a space of the point cloud. Then the processing circuitry determines, based on information of one or more other nodes, a single isolated point flag for the current node that indicates whether the current node is coded with a single isolated point.

Abstract: Aspects of the disclosure provide a method and an apparatus for video encoding. Whether a block size cbSize of a chroma block in luma samples is less than or equal to a minimum allowed chroma quaternary tree (QT) leaf node size MinQtSizeC in luma samples such that cbSize <=MinQtSizeC is determined. In response to the block size cbSize of the chroma block in luma samples being less than or equal to the minimum allowed chroma QT leaf node size MinQtSizeC in luma samples, a QT split is determined as disallowed for the chroma block. Partition information indicating that a chroma coding tree structure in a dual tree is applied to the chroma block is generated, the partition information further indicating the block size cbSize of the chroma block in luma samples and the minimum allowed chroma QT leaf node size MinQtSizeC in luma samples.

Abstract: A method of video coding includes receiving video data comprising one or more subpictures, signaling, in a sequence parameter set, whether to use a network abstraction unit (NAL) layer identifier as a subpicture identifier, signaling the subpicture identifier in a NAL unit header when the sequence parameter set indicates to use the NAL layer identifier and signaling the subpicture identifier in a slice header when the sequence parameter set indicates not to use the NAL layer identifier, signaling a length of the subpicture identifier, and encoding the video data based on the subpicture identifier.

Abstract: A method and system for decoding a coded video sequence may include obtaining the coded video sequence, and decoding the coded video sequence. A a value of a temporal sublayer identifier of a video coding layer (VCL) network abstraction layer (NAL) unit in the coded video sequence is constrained to be less than or equal to a value of vps_max_sublayers_minus1, that specifies a maximum number of temporal sublayers that may be present in a layer in each coded video sequence referring to the video parameter set (VPS), in the VPS referred to by the VCL NAL unit.

Abstract: Method, apparatus, and system for merging multiple attribute maps for mesh compression may be provided. The process may include obtaining multiple attribute maps associated with a mesh including one or more texture maps. The multiple attribute maps may be concatenated into a single concatenated map and concatenated UV coordinates for each of the multiple attribute maps may be generated based on re-computing original UV coordinates of each of the multiple attribute maps within the single concatenated map.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding and decoding. The apparatuses include an apparatus for video decoding. Processing circuitry of the apparatus for video decoding can decode coded information for a current block from a coded video bitstream. The coded information indicates a bi-prediction motion compensation mode for the current block. The processing circuitry determines, based on current neighboring reconstructed samples of the current block, first neighboring reconstructed samples of a first prediction block, and second neighboring reconstructed samples of a second prediction block, a weight used in the bi-prediction motion compensation mode. The processing circuitry reconstructs samples in the current block based on a weighted average of corresponding samples in the first prediction block and the second prediction block using the determined weight.

Abstract: In a method of video decoding, coded information of a current block is received. First information associated with the current block in the coded information is obtained. The first information indicates whether the current block is intra predicted based on decoder side intra mode derivation (DIMD). Second information associated with the current block in the coded information is obtained. The second information indicates whether the current block is partitioned based on an intra sub-partition (ISP) mode. A context model index is determined in response to one of (i) the first information indicating that the current block is intra predicted based on the DIMD, and (ii) the second information indicating that an above adjacent block or a left adjacent block of the current block is partitioned based on the ISP mode. The current block is decoded from the coded video stream based at least on the context model index.

Abstract: A method of video encoding includes determining whether a plurality of constraint flags of a constraint information group are to be signaled for a subset of coding blocks, and signaling a gate flag indicating whether the plurality of constraint flags of the constraint information group are signaled. The gate flag is signaled in constraint information in a syntax structure of a coded video bitstream. In accordance with the signaled gate flag indicating that the plurality of constraint flags of the constraint information group are signaled, the method further includes signaling the plurality of constraint flags of the constraint information group in the constraint information in the syntax structure of the coded video bitstream. In accordance with the plurality of constraint flags being signaled in the constraint information, the method further includes encoding the subset of coding blocks based on the plurality of constraint flags.

Abstract: This disclosure relates generally to video coding and particularly to methods and systems for providing signaling schemes for jointly coding of motion vector difference. An example method for decoding a current video block of a video bitstream is disclosed. The method includes receiving a coded video bitstream; determining, from the coded video bitstream, a flag for a current video block, wherein the flag indicates whether joint motion vector difference (MVD) coding is applied to the current video block; and in response to the flag indicating that the joint MVD coding is applied to the current video block: obtaining, by the device from the coded video bitstream, a joint MVD for the current video block, deriving, by the device based on the joint MVD, an MVD for the current video block, and decoding, by the device based on the joint MVD and the derived MVD, the current video block.

Abstract: Aspects of the disclosure provide method and apparatus for video coding. In some examples, an apparatus includes receiving circuitry and processing circuitry. The processing circuitry selects a reference line from a plurality of potential reference lines and selects an intra prediction mode from a set of potential intra prediction modes that is associated with the reference line. The processing circuitry encodes a block according to the intra prediction mode and at least one reference sample in the reference line. The processing circuitry further generates prediction information of the block. Inclusion of an indication of a reference line index of the reference line in the prediction information is based on the intra prediction mode.

Abstract: A method, computer program, and computer system is provided for decoding point cloud data. Data corresponding to a point cloud is received. A number of contexts associated with the received data is reduced based on reducing a size of an array corresponding to syntax elements for predictive tree-based coding of the point cloud. The data corresponding to the point cloud is decoded based on the reduced number of contexts.

Abstract: A method, device, and computer-readable medium for decoding an encoded video bitstream using at least one processor, including obtaining a flag indicating that a conformance window is not used for reference picture resampling; based on the flag indicating that the conformance window is not used for the reference picture resampling, determining whether a resampling picture size is signaled; based on determining that the resampling picture size is signaled, determining a resampling ratio based on the resampling picture size; based on determining that the resampling picture size is not signaled, determining the resampling ratio based on an output picture size; and performing the reference picture resampling on a current picture using the resampling ratio.

Abstract: Methods and systems are provided for decoding at least one video stream. A method includes receiving a first network abstraction layer (NAL) unit of a first slice of a coded picture and a second VCL NAL unit of a second slice of the coded picture, the first VCL NAL unit having a first VCL NAL unit type and the second VCL NAL unit having a second VCL NAL unit type that is different from the first VCL NAL unit type, and decoding the coded picture, the decoding including determining a picture type of the coded picture based on the first VCL NAL unit type of the first VCL NAL unit and the second VCL NAL unit type of the second VCL NAL unit, or based on an indicator, received by the at least one processor, indicating that the coded picture includes mixed VCL NAL unit types.

Abstract: In a method, a base mesh is generated from a down-sampled input mesh in a current frame, where the base mesh includes a plurality of vertices. A prediction mode to be applied to the base mesh is determined. The prediction mode is an inter prediction mode or an intra prediction mode. Based on the prediction mode being determined as the intra prediction mode, duplicate vertices among the plurality of vertices in the base mesh are merged to generate a subset of the plurality of vertices. At least the subset of the plurality of vertices is encoded based on the determined intra prediction mode to generate prediction information of at least the subset of the plurality of vertices.

Abstract: In a method, coded information of a current block in a current picture of a video is received from a coded video bitstream. The coded information indicates that the current block is partitioned into at least a first partition and a second partition based on a geometric partition mode (GPM). The first partition is associated with an intra block copy (IBC) prediction mode, and the second partition is associated with an intra prediction mode. Prediction mode information for a first subblock of a plurality of subblocks of the current block is stored. The prediction mode information includes one of a DC mode, a Planar mode, and an intra prediction mode based on whether the first subblock is associated with one of the IBC prediction mode, the intra prediction mode, and both the IBC prediction mode and the intra prediction mode.

Abstract: A method and apparatus for decoding multiple semantically independent picture parts into a single video picture includes decoding unique picture order count values for each coded picture, coded slice, or coded tile in a coded video sequence, with multiple decoded pictures, cycles, and tiles belonging to a same access unit representing a frame of the video. A value representing the amount of pictures, cycles, or tiles, is then assigned to each access unit for assigning sequential access unit count values to the access units. As a result, each access unit, which represents multiple pictures, slices, or tiles to be combined into a single frame, is decoded for display processing.

Abstract: A method of decoding image data is provided. The method may include generating a dequantized block of an image based on a coded bitstream; determining whether to use one from among an implicit method and an explicit method for selecting a hybrid transform kernel from among one or more hybrid transform kernel that are available for decoding the dequantized block, wherein the one or more hybrid transform kernel are available for decoding the dequantized block based on associations between prediction modes and sizes of blocks; selecting, by using the one from among the implicit method and the explicit method, the hybrid transform kernel from among the one or more hybrid transform kernel; and performing inverse transform coding of the dequantized block based on the selected hybrid transform kernel.

Abstract: This disclosure relates generally to video coding/decoding and particularly to motion vector prediction based on subblock motion vectors. One method is disclosed for processing a current block of a current frame in a coded video bitstream. The method includes receiving, by a device, a coded video bitstream; determining, by the device based on the coded video bitstream, the current block of the current frame to be inter predicted by at least one reference block of at least one reference frame; determining, by the device based on the coded video bitstream, a current-block motion vector (MV) corresponding to each of the at least one reference block, the current-block MV to be predicted by a reference MV; and identifying, by the device, a subblock MV of a MV reference block as the reference MV for predicting the current-block MV.