Abstract: This disclosure generally relates to media application development and deployment using an NBMP system. More specifically, this disclosure describes methods and apparatuses for instance level configuration of functions used in NBMP workflows. Example mechanisms are provided for configuring different instances of a same function in various tasks in a media processing workflow with customized configurations and restrictions based on a format of a general configuration descriptor of the function.

Abstract: Aspects of the disclosure provide a method and an apparatus for video decoding. The apparatus includes processing circuitry receiving prediction information of a plurality of blocks in a current picture from a coded video bitstream. The processing circuitry determines, based on the prediction information, whether at least one of a decoder-side motion vector refinement (DMVR) mode or a bi-directional optical flow (BDOF) mode is allowed for the plurality of blocks. If the DMVR mode or the BDOF mode is allowed for the plurality of blocks, the processing circuitry determines that a plurality of merge with motion vector difference (MMVD) merge flags indicating whether a MMVD mode is applied to the plurality of blocks, respectively, is inferred as false for the plurality of blocks. If the plurality of MMVD merge flags is inferred as false, the processing circuitry reconstructs each block in the plurality of blocks without applying the MMVD mode.

Abstract: Methods and apparatuses for video encoding/decoding are provided. In some examples, an apparatus for video decoding includes receiving circuitry and processing circuitry. The processing circuitry decodes prediction information of a current block in a current picture from a coded video bitstream. The prediction information is indicative of an inter prediction mode. Then, the processing circuitry determines a usage of a first DMVD process on the current block at least partially based on a second DMVD process not being used on the current block. Further, the processing circuitry reconstructs the current block according to the inter prediction mode with the first DMVD process.

Abstract: A method and apparatus for performing a frequency-dependent joint component secondary transform (FD-JCST). The method includes obtaining a plurality of transform coefficients in a transform coefficient block; determining whether at least one of the plurality of transform coefficients is a low-frequency coefficient; based on determining that the at least one of the plurality of transform coefficients is the low-frequency coefficient, determining whether the low-frequency coefficient is a non-zero value; and based on determining that the low-frequency coefficient is the non-zero value, performing a joint component secondary transform (JCST) on the low-frequency coefficient and signaling a related syntax to indicate that the JCST is performed.

Abstract: In a teleconferencing method, a first media stream and a second media stream of a teleconference are received, by processing circuitry of a first device, from a second device. The first media stream includes first audio and the second media stream includes second audio. Default weight information is received from the second device. The default weight information indicates a first audio weight for weighting the first audio and a second audio weight for weighting the second audio. The first audio weight for weighting the first audio and the second audio weight for weighting the second audio are determined based on the default weight information. Mixed audio is generated, by the processing circuitry of the first device, by combining a weighted first audio based on the first audio weight applied to the first audio and a weighted second audio based on the second audio weight applied to the second audio.

Abstract: A method of encoding video data corresponding to a point cloud by at least one processor, the method including obtaining a plurality of transform coefficients corresponding to attributes of the point cloud; and encoding the plurality of transform coefficients to generate an embedded bitstream, the encoding including iterating over a plurality of bit-planes of the plurality of transform coefficients to process all points in the point cloud.

Abstract: Methods, apparatus, and computer readable storage medium for intra prediction mode coding in video decoding. The method includes receiving, by a device, a coded video bitstream for a block. The device includes a memory storing instructions and a processor in communication with the memory. The method also includes dividing, by the device, a list of intra modes into a plurality of intra mode sets for the block based on mode information of each intra mode in the list, the list of intra modes corresponding to an intra prediction mode of at least one neighboring block of the block; extracting, by the device from the coded video bitstream, a set index indicating an intra mode set from the plurality of intra mode sets; extracting, by the device from the coded video bitstream, a mode index indicating an intra prediction mode from the intra mode set; and determining, by the device, the intra prediction mode for the block based on the set index and the mode index.

Abstract: A method of utilizing an 8-bit primary transform core matrix to decode compressed video or image data or encode uncompressed video or image data. The method may include determining whether to use a first transform core matrix that is of a first size type or a second transform core matrix that is of a second size type that is smaller than the first size type. When a result of the determination is to use the first transform core matrix, encoding or decoding the target file using the 8-bit primary transform core matrix that has the size that is 64-point or larger. If not, the method may include extracting the second transform core matrix of the second size type from the first transform matrix and encoding or decoding the target file using the extracted second transform core matrix.

Abstract: Methods, apparatus, and computer readable storage medium for intra bi-prediction and multiple reference line intra prediction in video decoding. The method includes receiving, by a device, a coded video bitstream for a block. The method also includes determining, by the device, whether a single directional intra prediction or an intra bi-prediction applies to the block, based on mode information of the block, the mode information of the block comprising at least one of: a reference line index of the block, an intra prediction mode of the block, and a size of the block; in response to determining that the single directional intra prediction applies to the block, performing, by the device, the single directional intra prediction to the block; and in response to determining that the intra bi-prediction applies to the block, performing, by the device, the intra bi-prediction to the block.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to obtain a mesh sequence comprising a plurality of meshes corresponding to volumetric data of at least one three-dimensional (3D) visual content, obtain a frame of the mesh sequence corresponding to the volumetric data, the frame including a plurality of vertices of a mesh of the mesh sequence, determine a motion field comprising motion vectors of the plurality of vertices of the mesh, and encode the volumetric data based on the motion field.

Abstract: Aspects of the disclosure provide methods and apparatuses for point cloud processing. In some examples, an apparatus for point cloud processing includes processing circuitry. For example, the processing circuitry obtains point cloud data corresponding to a point cloud in a three dimensional (3D) space, projects the point cloud in the 3D space to one or more two dimensional (2D) planes to generate one or more images. The processing circuitry generates a pixel wise mask for object instances in the point cloud according to the one or more images. The pixel wise mask includes first pixels that are associated with a first object instance in the point cloud. The processing circuitry processes the point cloud based on the pixel wise mask, a portion of the point cloud corresponding the first pixels in the pixel wise mask is processed based on one or more processing parameters determined for the first object instance.

Abstract: A method, computer program, and computer system for enabling peer-to-peer media streaming using service enabler architecture layer (SEAL). The method may be executed by one or more processors, and the method may include receiving, by a vertical application layer (VAL) server, a request for a media session negotiation between one or more client devices, and retrieving, by the vertical application layer (VAL) server, transport layer information associated with each of the one or more client devices using network address translation traversal. The method may further include transmitting, by the vertical application layer (VAL) server, agreed session description protocol (SDP) parameters based on the transport layer information, wherein the agreed session description protocol (SDP) parameters are used to establish a peer-to-peer media streaming session.

Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform obtaining an input low resolution (LR) image comprising a height, a width, and a number of channels, implementing a feature learning deep neural network (DNN) configured to compute a feature tensor based on the input LR image, generating, by an upscaling DNN, a high resolution (HR) image, having a higher resolution than the input LR image, based on the feature tensor computed by the feature learning DNN, wherein a networking structure of the upscaling DNN differs depending on different scale factors, and wherein a networking structure of the feature learning DNN is a same structure for each of the different scale factors.

Abstract: A method, computer program, computer system, and device is provided for determining media sink capabilities. The method may include obtaining, by a media source, a sink resource associated with a media sink, wherein the sink resource indicates a direct address at which a capability described in the sink resource can be directly accessed; and accessing the capability directly by the media source using the direct address.

Abstract: Systems and methods for deep neural network (DNN)-based cross component prediction are provided. A method includes inputting a reconstructed luma block of an image or video into a DNN; and predicting, by the DNN, a reconstructed chroma block of the image or video based on the reconstructed luma block that is input. Luma and chroma reference information and side information may also be input into the DNN to predict the reconstructed chroma block. The various inputs may also be generated using processes such as downsampling and transformation.

Abstract: A method of controlling intra-inter prediction for decoding or encoding of a video sequence, is performed by at least one processor. The method may include setting a prediction mode flag associated with a current block to indicate whether the current block is coded in inter prediction mode, intra prediction mode, or inter-intra prediction mode; deriving a context value associated with a coded block flag associated with the current block based on the prediction mode flag associated with the current block. Deriving the context value may include based on the current block being determined to be coded in the intra prediction mode, setting the context value of the coded block flag to a first value, and based on the current block being determined to be coded in the inter prediction mode, setting the context value of the coded block flag to a second value.

Abstract: Method, apparatus, and non-transitory storage medium for end-to-end neural image compression using dependent scalar quantization with substitution, including receiving an input image; determining a substitute image based on the input image using a neural network based substitute feature generator; compressing the substitute image; quantizing the compressed substitute image to obtain a quantized representation of the input image with higher compression performance by using a first dependent scalar quantizer; and entropy encoding the substitute image using a neural network based encoder to generate a compressed representation of the quantized representation.

Abstract: The various embodiments described herein include methods, devices, and systems for generating object meshes. In some embodiments, a method includes obtaining a trained classifier, and an input observation of a 3D object. The method further includes generating a three-pole signed distance field from the input observation using the trained classifier. The method also includes generating an output mesh of the 3D object from the three-pole signed distance field; and generating a display of the 3D object from the output mesh.

Abstract: A method for controlling block intra prediction is provided for a decoder. The method includes: obtaining a coded video bitstream; decoding, prediction information of a current coding unit (CU) in a segment of a current picture from the coded video bitstream; determining, according to the prediction information, a prediction type of a chroma coding block (CB) of the current CU, the prediction type being intra prediction or inter prediction; and reconstructing the chroma CB according to the prediction information, where a width of any reconstructed chroma CB intra-predicted from the coded video bitstream is greater than 2.

Abstract: A method, computer program, and computer system is provided for coding a video sequence. Video data comprising one or more luma samples is received. A YUV format associated with the received video data is determined. A height setting value and a width setting value corresponding to the one or more luma samples are restricted based on the determined YUV format. The YUV format may include a YUV4:4:4 format, a YUV4:2:2 format, a YUV4:2:0 format, and a YUV4:0:0 format.