Abstract: Aspects of the disclosure include methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. An apparatus includes processing circuitry that decodes prediction information of a current block that is a part of a current picture in a video bitstream. The prediction information indicates a reference block for the current block. The processing circuitry generates filter coefficients of a filter operation based on neighboring reconstructed samples of the current block and neighboring reconstructed samples of the reference block that are co-located with the neighboring reconstructed samples of the current block. The filter operation compensates local changes to the current picture, such as illumination change or motion blur. The processing circuitry determines a prediction block for the current block based on the filter operation being performed on the reference block of the current block.

Abstract: A method is provided for generating virtual units in a virtual scene at a computing device. The method includes displaying, on a display device, a user interface (UI) that includes a plurality of build elements comprising a first set of build elements corresponding to generating virtual units available to a user and a second set of build elements corresponding to generating or upgrading virtual objects available to the user. The plurality of build elements in the UI may include a union set of all virtual unit generation, build, and upgrade actions available to the user. The method also includes receiving a user input indicating a selection of a build element among the plurality of build elements in the UI. The method further generating a virtual unit, generating a virtual object, or upgrading an existing virtual object in the virtual scene according to the selection of the build element.

Abstract: Methods and apparatuses for video coding are provided. Processing circuitry in one of the apparatuses receives a coded video bitstream that includes prediction information of a chroma block to be reconstructed in a current picture. The prediction information indicates that the chroma block is predicted based at least on a luma block in the current picture. The luma block is reconstructed and collocated with the chroma block. The processing circuitry predicts one or more first chroma samples in the chroma block based on one or more luma samples in the luma block and predicts a second chroma sample in the chroma block based on the predicted one or more first chroma samples and at least one reference chroma sample of the chroma block. The second chroma sample is different from the one or more first chroma samples. The at least one reference chroma sample is adjacent to the chroma block.

Abstract: An example real-time simulation framework for a fluid and granular substance mixture is disclosed. Such a framework may be based on modeling height fields and horizontal velocities of different material phases, which in the context of a water-sand system, may include sand, water, and mixed water. The framework achieves a trade-off between simulation fidelity and performance, providing real-time computation for interactive applications. The example framework formulates the external frictional force and elastoplastic internal force of sand based on horizontal grid and further handles the water/sand coupling via diffusion and momentum exchange. The time updates for the simulation is efficiently performed using a semi-implicit operator splitting discretization scheme and an asynchronous scheme for the fluid and the granular substance.

Abstract: A method, computer program, and computer system is provided for coding video data. Video data is received, and an edge present within a sample of the received video data is detected. A gradient value corresponding to a direction associated with the detected edge is calculated. The video data is decoded based on the calculated gradient.

Abstract: Methods and systems for decoding a video stream are provided, a method comprises receiving a coded video stream comprising a picture partitioned into a plurality of tile groups, each of the plurality of tile groups include at least one tile, the coded video stream further comprising a first indicator that indicates whether a tile group of the plurality of tile groups has a rectangular shape; identifying whether the tile group of the picture has the rectangular shape based on the first indicator; and reconstructing, forwarding, or discarding the tile group.

Abstract: This disclosure relates transform configuration and signaling for a compound inter-intra prediction modes. In one example, a method for decoding a video block in a video stream is disclosed. The method may include determining that the current block is predicted under a CIIP mode; generating a set of secondary transform coefficients for the current block from the video bitstream; applying a combined inter intra secondary transform by: performing an inverse separable or non-separable secondary transform on the set of secondary transform coefficients to obtain a set of primary transform coefficients of the current block; and performing an inverse primary transform on the set of primary transform coefficients to obtain a residual block of the current block; and decoding, under the CIIP mode, the current block from the residual block.

Abstract: This disclosure relates generally to coding and decoding of 3-dimensional (3D) mesh and specifically to fast and efficient packing of parts of a 3D mesh into a map in a 2-dimensional (2D) space. In one example, a 3D mesh frame is decomposed into charts. The charts are iteratively projected and packed into a 2D map to achieve improved compactness by using an image filtering technology. The image filtering technology may involve perform efficient convolution and correlation processing using fast Fourier transform.

Abstract: Systems and methods for scheduling a network-based media processing (NBMP) workflow based on a scheme mode are provided. The scheme mode may be obtained by a NBMP workflow manager based on received information that indicates the scheme mode. The NBMP workflow manager may schedule tasks of the NBMP workflow to be executed to process media in accordance with the scheme mode indicated in the information. The scheme mode may be a by order mode, a by duration mode, a by event mode, or a by timeslot mode.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. Processing circuitry in an apparatus decodes coded information of a coding unit (CU) from a coded video bitstream. The coded information indicates a last position of non-zero transform coefficients of a first coding block (CB) of the CU. The processing circuitry determines whether a secondary transform index is signaled in the coded information based at least on comparison to a threshold value and whether to perform a secondary transform on a second CB of the CU based on whether the secondary transform index is determined to be signaled in the coded information. When the secondary transform is determined to be performed, the processing circuitry performs the secondary transform on the second CB and reconstructs the second CB. When the secondary transform is determined not performed, the second CB is reconstructed without performing the secondary transform on the second CB.

Abstract: In a method for video encoding, whether an angular intra prediction mode for a current block is a wide angle mode is determined. The current block is a non-square block and the wide angle mode is in a direction outside of a range of directions that spans a bottom left diagonal direction and top right diagonal direction of the current block. In response to determining that the angular intra prediction mode is the wide angle mode, whether a block size of the non-square block is greater than 32 is determined. In response to determining that the block size of the non-square block is greater than 32, an intra smoothing filter is enabled and the enabled intra smoothing filter is applied to blocks neighboring the current block to generate filtered blocks. A characteristic value of the current block is encoded in a bitstream based on the filtered blocks.

Abstract: A method of video decoding includes creating a candidate list for a current block in a current picture included in a coded video bitstream. The method further includes determining a coding mode for a candidate block associated with the current block. The method further includes determining whether to add, to the candidate list, a vector associated the candidate block based on the determined coding mode. The method further includes reconstructing the current block using at least one candidate from the candidate list.

Abstract: A method and system for audio mixing in a teleconference using a Session Description Protocol (SDP) and Real-time Transport Protocol (RTP) signaling of audio mixing gain is provided. The method includes receiving an input audio stream from a 360-degree video/audio stream that includes an audio mixing gain which includes audio gain from the input audio stream and audio gain from overlay audio streams, declaring a RTP header extension for the input audio stream using the SDP, the RTP header extension, and signaling the audio mixing gain based on a single attribute of the SDP using the RTP header extension. An element of the RTP header extension may include an element identifier, a length of an extension element, and a magnitude of the audio mixing gain of the RTP header extension. The RTP header extension may use a one-byte or two-byte header extension format which is declared using the SDP.

Abstract: This disclosure relates to adaptively reordering reference frames for video coding technologies. Template matching (TM) may be used to reorder the reference frames or reference frame pairs for each block by comparing the difference between the template of a current block and the template of a reference block with reference to the motion information of the spatial reference motion information (or spatial motion vectors) and/or temporal reference motion information (or temporal motion vectors). The difference between the template of current block and the template of the reference block may be calculated for each spatial reference motion information and/or temporal reference motion information, and marked as the score value of the associated reference frames or reference frame pairs. The available reference frames or reference frame pairs are ranked based on the score value.

Abstract: A filter with a central symmetric shape is applied to a current block. The filter includes a plurality of coefficients. Each of the plurality of coefficients is associated with a respective first coordinate value along a first axis and a respective second coordinate value along a second axis. The plurality of coefficients of the filter is grouped into a plurality of groups based on a transposition operation to be performed on the filter. The coefficients in each of the plurality of groups is a same distance from a center position of the filter. The coefficients of a first group of the plurality of groups are reordered based on the transposition operation. Filtered samples of the current block are reconstructed by applying the filter with the central symmetric shape to the current block based on the reordered coefficients of the filter.

Abstract: Systems and methods for receiving a coded video bitstream including a current frame, a first reference frame and a second reference frame associated with a current block in the current frame, a joint motion vector difference (JMVD) associated with the first reference frame and the second reference frame, and a flag indicating whether one or more scaling factors are used to derive a motion vector difference (MVD) from the JMVD. A first/second MVD associated with the first/second reference frame may be derived based on applying a first/second scaling factor in the one or more scaling factors to the JMVD or based on a distance between the first/second reference frame and the current frame. The current block may be decoded based on the first MVD and the second MVD.

Abstract: A method of encoding a mesh includes determining a symmetry plane that divides the mesh into a first side and a second side opposite the first side, the mesh comprising a plurality of vertices, the first side comprising a first set of vertices, the second side comprising a second set of vertices; determining, for each vertex in the first set, a predicted vertex on the second side that is symmetric to a corresponding vertex in the first set; determining a transformation function that transforms each predicted vertex on the second side, the transformation function determined in accordance with a loss function; applying the transformation function that transforms each predicted vertex on the second side; determining a displacement vector between each transformed predicted vertex and a corresponding vertex in the second set; and generating a bitstream that comprises each encoded vertex in the first set and each displacement vector.

Abstract: In a method of decoding, a first flag of a sequence parameter set (SPS) that is referred to by a current picture is obtained. The current picture is decoded based on whether the first flag indicates the reference picture resampling is enabled. The first flag equal to a first value indicates that the reference picture resampling is enabled and the current picture is allowed to include slices that refer to a reference picture with at least one of a different spatial resolution or a different scaling window in an active entry of a reference pictures list. The first flag equal to a second value indicates that the reference picture resampling is disabled and no slice of the current picture refers to the reference picture with the at least one of the different spatial resolution or the different scaling window in the active entry of the reference picture list.

Abstract: This disclosure relates generally to video coding and particularly to methods and systems for deriving offsets in cross-component transform coefficient level reconstruction. An example method for decoding a current video block of a video bitstream is disclosed. The method includes receiving a coded video bitstream; extracting, from the coded video bitstream, a first transform coefficient of a first color component for a current video block; determining a second transform coefficient of a second color component for the current video block; deriving an offset value based on at least one of the following: a quantization step size, or the first transform coefficient; adding the offset value to the second transform coefficient to generate a modified second transform coefficient for the second color component; and decoding the current video block based on the first transform coefficient and the modified second transform coefficient of the second color component.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to receive a video bitstream comprising a current block in a current picture and reconstruct the current block by transforming the current block by a neural network comprising a plurality of upsample modules and activation modules, and at least one of the activation modules includes a LeakyReLu function and a convolution function.