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 of directing content preparation for a 5G media streaming (5GMS) network performed by at least one processor implementing a 5GMS application provider, the method comprising creating a content preparation template, by the 5GMS application provider, wherein the content preparation template includes first information specifying instructions for content preparation, and second information specifying instructions for content output; establishing a first provisioning session with a 5GMS application function; transmitting the content preparation template to the 5GMS application function in the first provisioning session, wherein the 5GMS application function requests to allocate 5GMS content preparation resources and 5GMS content distribution resources; and receiving a first acknowledgement from the 5GMS application function, wherein the first acknowledgement indicates an allocation of at least one of content preparation resources and content distribution resources.

Abstract: A method for video encoding includes determining an intra prediction angle for encoding a current block in a coded video sequence, the intra prediction angle being (i) beyond a bottom left direction diagonal mode, or (ii) beyond a top right direction diagonal mode. The method further includes determining an intra prediction mode corresponding to the intra prediction angle used to encode the current block based on a predetermined relationship between a plurality of intra prediction modes and a corresponding plurality of intra prediction angles, and generating prediction information indicating the determined intra prediction mode corresponding to the intra prediction angle used to encode the current block.

Abstract: A method, computer program, and computer system is provided for compressing a neural network model. One or more indices corresponding to a multi-dimensional tensor associated with a neural network are reordered. A set of weight coefficients associated with the one or more reordered indices is unified. A model of the neural network is compressed based on the unified set of weight coefficients.

Abstract: A method, computer program, and computer system is provided for coding video data. Video data including a current picture and one or more other pictures is received. A first flag corresponding to whether the current picture is referenced by the one or more other pictures in a decoding order is checked. A second flag corresponding to whether the current picture is output; is checked. The video data is decoded based on values corresponding to the first flag and the second flag.

Abstract: A method, computer program, and computer system are provided for video coding. The video coding includes decoding one or more previously encoded frames of a video source that are designated as reference frames for the video source, searching the reference frames for one or more candidate pixel blocks for an input frame of the video source, and encoding the input frame based on the one or more candidate pixel blocks.

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: Methods, apparatus, and computer readable storage medium for entropy coding for intra prediction modes in video encoding and/or decoding. The method includes receiving, by a device, a coded video bitstream for a block; deriving, by the device, at least one context for a set index and a mode index for the block based on at least one of the following: information of the block and mode information of at least one neighboring block of the block, wherein: the set index indicates an intra mode set from a plurality of intra mode sets, and the mode index indicates an intra prediction mode from the intra mode set; extracting, by the device from the coded video bitstream, the set index and the mode index according to the at least one context; and determining, by the device, the intra prediction mode for the block based on the set index and the mode index.

Abstract: A method and an apparatus for video decoding are provided. The apparatus includes processing circuitry that decodes prediction information of one or more blocks including a current block from a coded video bitstream. The prediction information indicates that local illumination compensation (LIC) is applied to the one or more blocks and includes LIC information of the one or more blocks. The processing circuitry determines a final scaling factor ?_f1 and a final offset ?_f1 of a first subblock in the current block based on the LIC information. The processing circuitry determines an updated first predictor subblock in a predictor corresponding to the current block based on the final scaling factor ?_f1, the final offset ?_f1, and the first predictor subblock. An updated value of a first sample in the first predictor subblock is equal to ?_f1×p_i1+?_f1. p_i1 is a value of the first sample.

Abstract: A method and apparatus for reducing artifacts in a compressed image using a neural-network based deblocking filter. The method may include receiving at least one reconstructed image, wherein each reconstructed image comprises one or more reconstructed blocks and extracting boundary areas associated with boundaries of the one or more reconstructed blocks in the at least one reconstructed image. The extracted boundary areas may be input in a trained deblocking model to generate boundary areas having reduced artifacts and the trained deblocking mode is trained on training data based on estimated compression by a neural image compression (NIC) network. The edge areas associated with the generated boundary areas may be removed; and at least one reconstructed image with reduced artifacts may be generated based on the generated boundary areas.

Abstract: Method, apparatus, and non-transitory storage medium for coding and decoding video data using temporal motion vector prediction (TMVP) is provided. The method may include receiving video bitstream comprising one or more pictures; determining that the one or more pictures are to be predicted in a regular merge mode or an adaptive motion vector prediction (AMVP) mode. A displacement vector associated with a current block in a current picture is obtained, the displacement vector being signaled in the video bitstream to identify a reference block in the current picture. A TMVP candidate list comprising the motion information is generated and a motion vector for the current block using the TMVP candidate list is derived. Then the current block is decoded using the derived motion vector for prediction in the regular merge mode or the adaptive motion vector prediction (AMVP) mode.

Abstract: A method and apparatus may be provided for signaling auxiliary media content over a (DASH) media stream. The method may include receiving one or more auxiliary descriptors, wherein a respective auxiliary descriptor among the one or more auxiliary descriptors includes a Uniform Resource Locator (URL) referencing one or more auxiliary media presentation descriptions (MPDs) and a stack mode value indicating a stack operation supported by a main DASH media stream. The method may also include retrieving one or more auxiliary media segments based on the URL referenced in the respective auxiliary descriptors among the one or more auxiliary descriptors, and playing the one or more auxiliary media segments and the one or more main DASH media segments from a media source extension (MSE) source buffer at least once in at least one order based on the one or more auxiliary descriptors and the stack mode value.

Abstract: A method of video encoding includes determining whether a reference block for a current block is located in a different coding tree unit (CTU) than a CTU of the current block. The method also includes, in response to the reference block being located in the different CTU, (i) determining whether a memory location of a reference sample memory for the reference block is available. The second area is collocated in the different CTU with a position of the first area in the CTU of the current block. In response to the determination that the reference block is located in the different CTU, the method also includes, (ii) in response to a determination that the memory location for the reference block is available, retrieving, from the memory location corresponding to the reference block, one or more samples to encode the current block.

Abstract: In a method of video encoding, whether a picture of a sequence of pictures is a flash picture that is associated with a scene change between (i) a first scene of the picture of the sequence of pictures and (ii) a second scene of a prior picture and a subsequent picture of the picture in the sequence of pictures, the scene change being determined based on a content change between the first scene and the second scene being larger than a threshold is determined. An encoding process is performed on the picture in the sequence of pictures based on whether the picture is determined as the flash picture. A configuration of a coding tool in the encoding process is adjusted when the picture is determined as the flash picture.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to receive an audio signal obtained from a microphone, input the audio signal into a neural-network based AHS model, wherein the neural-network based AHS model is trained using a training audio signal, and output an AHS signal from the neural-network based AHS model in which AHS is applied to the audio signal, wherein the AHS signal is a version of the audio signal in which acoustic howling noise of the audio signal is suppressed and target audio of the audio signal is sustained.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to receive an audio signal obtained from a microphone, input the audio signal into a neural-network based AEC model, and output an AEC signal from the neural-network based AEC model in which AEC is applied to the audio signal, and the AEC signal is a version of the audio signal in which acoustic echo noise of the audio signal is suppressed and target audio of the audio signal is sustained.

Abstract: This disclosure relates generally to video coding/decoding. One method performed by a decoder includes receiving a video bitstream comprising a current picture, the current picture comprising a current block, and the current block comprising a current transform block; determining a skip transform flag indicating whether the current transform block has all zero coefficient or not via one of: receiving the skip transform flag from the video bitstream; or deriving the skip transform flag; deriving, based on the skip transform flag, at least one of following flags: an flag indicating whether Intra Block Copy is applied to the current block; an interPrediction flag indicating whether the current block is coded in inter-prediction mode; and reconstructing the current block based on at least one of: the IntraBC flag, the interPrediction flag.

Abstract: In a method of decoding performed in a decoder, a syntax element indicating a prediction mode associated with a current block in a current picture is received, the prediction mode being one of a uni-prediction mode and a bi-prediction mode. When the bi-prediction mode is applied to a first subblock of a plurality of subblocks of the current block and one of (i) a boundary of a first reference subblock is beyond a boundary of a first reference picture or (ii) a boundary of a second reference subblock is beyond a boundary of a second reference picture, the first subblock of the current block is reconstructed based on the uni-prediction mode such that the first subblock is reconstructed based on one of the first reference picture and the second reference picture.

Abstract: This disclosure relates generally to video coding/decoding and particularly for improvement of signaled transform set. One method includes receiving a coded video bitstream; extracting, based on the coded video bitstream, a set of transform coefficients for the current block; determining, based on a syntax element explicitly signaled in the coded video bitstream, a transform set index for the current block in an intra prediction mode, the transform set index indicating a transform set among a plurality of transform sets; identifying the transform set according to the transform set index; performing an inverse transform using the set of transform coefficients and the identified transform set to obtain a residual block for the current block; and reconstructing, by the device, the current block based on the residual block.

Abstract: An unsupervised text to speech system utilizing a lexicon to map input text to the phoneme sequence, which is expanded to the frame-level forced alignment with a speaker-dependent duration model. An alignment mapping module that converts the forced alignment to the unsupervised alignment (UA). Afterword, a Conditional Disentangled Sequential Variational Auto-encoder (C-DSVAE), serving as the self-supervised TTS AM, takes the predicted UA and a target speaker embedding to generate the mel spectrogram, which is ultimately converted to waveform with a neural vocoder.