Abstract: A method of decoding a bitstream to get one or more pictures for a video stream includes: receiving a bitstream; and decoding the bitstream to get the one or more pictures. The decoding includes: decoding a picture unit comprising one or more supplemental enhancement information (SEI) messages; and generating the one or more pictures based on a key picture and the one or more SEI messages, respectively.

Abstract: The present disclosure provides systems and methods for wrap-around motion compensation. One exemplary method comprises: receiving a wrap-around motion compensation flag; determining whether a wrap-around motion compensation is enabled based on the wrap-around motion compensation flag; in response to a determination that the wrap-around motion compensation is enabled, receiving data indicating a difference between a width of the picture and an offset used for determining a horizontal wrap-around position; and performing a motion compensation according to the wrap-around motion compensation flag and the difference.

Abstract: The present disclosure provides systems and methods for performing residual coding of video data. According to certain disclosed embodiments, the methods include: receiving control information for coding a video sequence; and determining, based on the control information, a coding method for coding a prediction residual signal of a coding block in the video sequence. The coding method is one of a transform residual coding and a transform-skip residual coding.

Abstract: The present disclosure provides a computer-implemented method for video processing. The method includes receiving a bitstream; and decoding the bitstream to form/generate/output a video sequence. The decoding includes decoding a flag indicating whether a subblock transform (SBT) intra mode is applied for a current coding unit (CU), wherein the current CU is coded in an intra prediction mode; in response to the flag indicating the SBT intra mode is applied, determining a sub-mode of the SBT intra mode; and decoding residuals of a sub-block based on the sub-mode.

Abstract: A method for encoding video data includes: determining motion vector predictors (MVP) for a target block based on control point motion vectors (CPMV), in which a bilinear model is represented by the CPMVs; determining motion vector differences (MVD), in which each motion vector difference is based on a difference between the corresponding MVP and the CPMV for each control point; and setting the MVDs in a bitstream, in response to the bilinear model being used.

Abstract: The present disclosure provides a computer-implemented method for video processing. The method includes receiving a video sequence; and encoding the video sequence by: determining a block size of a block; determining whether the block size is included in a first list; in response to the block size is not included in the first list, determining whether the block size is included in a second list; in response to the block size is included in the second list, selecting a neural network model for the block size and performing downsampling on the block based on the block size and the neural network model; and performing a neural network-based intra prediction (NNIP) on the block using the neural network model.

Abstract: A method of decoding a bitstream to output one or more pictures for a video stream includes: receiving a bitstream; and decoding, using coded information of the bitstream, one or more pictures. The decoding includes: determining a first motion vector predictor (MVP) and a second motion vector predictor (MVP) for a bi-predictive block coded in an advanced motion vector prediction (AMVP) mode, in which the first MVP is obtained from a first reference picture, and the second MVP is obtained from a second reference picture; and applying at least one of a decoder-side motion vector refinement (DMVR) process or a bilateral matching (BM) process based on a bilateral matching cost to refine at least one of the first MVP or the second MVP.

Abstract: The present disclosure provides computer-implemented methods for video processing. The method includes receiving a video sequence; and encoding the video sequence by determining whether a collocated block in a collocated picture of a current block has a block vector (BV); in response to the collocated block having the BV, determining the BV; determining a motion vector for Temporal Motion Vector Prediction (TMVP) for the current block based on the BV of the collocated block; and determining a reference index of the TMVP to be a reference index of the collocated picture.

Abstract: Embodiments contemplate coding video data by generating a video encoded bitstream that may include reference picture set (RPS) extensions for inter-layer reference pictures, and the extensions may include inter-layer delta Picture Order Counts (POCs). Embodiments may also include signaling that lower layer reference pictures may be available in a lower layer decoder picture buffer (DPB), and/or an aggregate DPB, that may be added to the RPS set of a higher layer. The bitstream may include a signal indicating whether the higher layer RPS may be specified by a lower layer RPS, and the lower layer RPS may be temporal, inter-layer prediction (ILP), or both.

Abstract: Methods and apparatuses are provided for encoding and decoding video data based on a supplemental enhancement information (SEI) message. An exemplary method includes: generating a reconstrued frame sequence based on a compressed video; decoding a supplemental enhancement information (SEI) message with respect to the reconstrued frame sequence, according to the compressed video; and performing temporal upsampling to the reconstrued frame sequence based on the SEI message by using a neural network.

Abstract: A VVC-standard encoder and a VVC-standard decoder are provided, implementing derivation of a BCW index according to cost values based on template matching. A template matching cost can be calculated for each among a set of possible BCW weight values, and a BCW weight value yielding a lowest template matching cost among each template matching cost calculated can be selected as a BCW index for a bi-predicted merge candidate. Alternatively, a template matching cost can be calculated for each among a subset of possible BCW weight values based on an inherited BCW weight. Additionally, a merge candidate BCW index can be derived while adjusting template matching cost of an inherited BCW weight from a value calculated according to the VVC standard and ECM specifications, or while adjusting template matching cost of a BCW weight having equal weight from a value calculated according to the VVC standard and ECM specifications.

Abstract: A method of encoding a video sequence into a bitstream. The method includes receiving a video sequence; performing a plurality of convolutions on an input image data of the video sequence in YUV format; wherein performing the plurality of convolutions includes performing a first stage convolution on the input image data, wherein the first stage convolution comprises a first convolution and a second convolution that are provided in parallel; performing a second stage convolution on a channel-wise concatenation result of an output of the first convolution and an output of the second convolution; performing a third stage convolution on an output of the second stage convolution; and obtaining an output image data based on an output of the third stage convolution; and encoding the output image data for generating the bitstream.

Abstract: Methods and apparatuses are provided for subblock-based temporal motion vector prediction (SbTMVP). An exemplary decoding method includes: decoding a target coding unit (CU) based on a SbTMVP mode, wherein the target CU is divided into a plurality of subblocks; determining a same reference picture index for the plurality of subblocks; selecting, based on the determined reference picture index, a reference picture from a list of reference pictures; generating a plurality of predicted subblocks based on the selected reference picture; and reconstructing the target CU based on the plurality of predicted subblocks.

Abstract: A method for frame extraction processing of a video includes obtaining an encoded image of a video sequence; obtaining presentation time stamps (PTSes) and non-reference frame flags of the encoded image, wherein the encoded image has an encoding structure with time domain levels; determining frame dropping positions of the video sequence based on the time domain levels, the PTSes, and the non-reference frame flags; and performing a frame extraction operation on the video sequence based on the frame dropping positions.

Abstract: An AVS3 and later-standard encoder and an AVS3 and later-standard decoder are provided, configuring one or more processors of a computing system to perform angular weighted prediction. The encoder and the decoder are configured to implement performing angular weighted prediction by constructing motion vector candidate lists including more MV candidates and additional types of MV candidates, and extending the candidate list length; by performing template matching based on reconstructed pixels surrounding the current block to reorder the MV candidates; and by performing motion vector refinement based on template matching to partitions of the current block.

Abstract: The present disclosure provides systems and methods for processing video content. The method can include: receiving data representing a first block and a second block in a picture, the data comprising a plurality of chroma samples associated with the first block and a plurality of luma samples associated with the second block; determining an average value of the plurality of luma samples associated with the second block; determining a chroma scaling factor for the first block based on the average value; and processing the plurality of chroma samples associated with the first block using the chroma scaling factor.

Abstract: A method for processing video includes receiving a bitstream; and decoding, using coded information of the bitstream, one or more pictures. The decoding includes performing overlapped block motion compensation (OBMC) on a block predicted with an intra mode.

Abstract: Embodiments of the present disclosure provide a loop filtering method, including: determining a reference image block corresponding to a to-be-processed image block in an adjacent reference frame in a time domain, and predicting the loop filtering enabling probability of the to-be-processed image block based on the result of loop filtering of the reference image block; determining spatial coding information of the to-be-processed image block, the spatial coding information being used to characterize texture complexity of the to-be-processed image block; and making a loop filtering decision for the to-be-processed image block in response to the spatial coding information and the loop filtering enabling probability meeting preset filtering conditions.

Abstract: Methods and apparatuses are provided for processing video data by using generative face video supplemental enhancement information (SEI) messages. An exemplary method for generating a face picture includes: receiving a bitstream; decoding coded information of the bitstream to obtain a base picture and a supplemental enhancement information (SEI) message; determining whether the SEI message applies to a neural network for generating a face picture; in response to the SEI message applies to the neural network for generating the face picture, determining a mode and a corresponding face information parameter used to code the face picture based on the SEI message; and generating the face picture based on the base picture and the face information parameter by the neural network.

Abstract: The present disclosure provides systems and methods for performing adaptive resolution change during video encoding and decoding. The methods include: comparing resolutions of a target picture and a first reference picture; in response to the target picture and the first reference picture having different resolutions, resampling the first reference picture to generate a second reference picture; and encoding or decoding the target picture using the second reference picture.