Abstract: A method of video decoding includes creating a candidate list for a current block in current picture included in a coded video bitstream. The method further includes determining a coding mode for at candidate block associated with the current block. The method further it 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: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes receiving circuitry and processing circuitry. For example, 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 a prediction mode that uses a first optical flow refinement coding tool. The first optical flow refinement coding tool uses a grid structure that is used additionally by at least a second optical flow refinement coding tool during operations of optical flow refinement. Then, the processing circuitry calculates, using the first optical flow refinement coding tool, refinements to predictions of samples of the current block based on the grid structure, and reconstructs the samples of the current block based on the refinements and the predictions of the samples.

Abstract: A pruning method of neural network based video coding of a current block of a picture of a video sequence is performed by at least one processor and includes categorizing parameters of a neural network into groups, setting a first index to indicate that a first group of the groups is to be pruned, and a second index to indicate that a second group of the groups is not to be pruned, and transmitting, to a decoder, the set first index and the set second index. Based on the transmitted first index and the transmitted second index, the current block is processed using the parameters of which the first group of the groups is pruned.

Abstract: In some examples, processing circuitry decodes, from a coded bitstream that carries a compressed image, an index that points a value in a set of values of a parameter. A value change of the parameter adjusts a compression rate of the compressed image. The compressed image is generated by a neural network based encoder based on the parameter. The processing circuitry inputs the value of the parameter into a multi-rate compression domain computer vision task decoder. The multi-rate compression domain computer vision task decoder includes one or more neural networks for performing a computer vision task from compressed images according to corresponding values of the parameter that are used for generating the compressed images. The multi-rate compression domain computer vision task decoder generates a computer vision task result according to the compressed image in the coded bitstream and the value of the parameter.

Abstract: A method, computer program, and computer system is provided for coding video data. Video data including one or more reference locations is received. The one or more reference locations are updated in a history list associated with the received video data based on intra block copy for a single value string mode. The video data is decoded based on the updated reference locations.

Abstract: Processing circuitry performs, based on an input image and a guideline image resulting of an image based computer vision task on the input image, an online training of a compression domain computer vision task framework (CDCVTF). The CDCVTF includes an encoding portion and a decoding portion. The encoding portion compresses the input image into a compression domain, and the decoding portion performs the image based computer vision task in the compression domain. The online training determines at least an update to a neural network in the decoding portion that reduces a loss between a result of the image based computer vision task in the compression domain and the guideline image. The processing circuitry encodes the input image into an encoded image, and forms a bitstream that carries the encoded image and additional bits. The additional bits are indicative of the update to the neural network in the decoding portion.

Abstract: A method performed by at least one processor in a decoder includes receiving a coded video bitstream that includes a compressed two dimensional (2D) mesh corresponding to a surface of three dimensional (3D) volumetric object. The method further includes predicting a current vertex included in the compressed 2D mesh based on an interpolation-based hierarchical prediction scheme that uses at least one sampled vertex included in the compressed 2D mesh. The method further includes deriving a prediction residual associated with the predicted current vertex. The method further includes reconstructing a boundary vertex associated with the 3D volumetric object based on the predicted current vertex and the derived prediction residual.

Abstract: A method performed in a decoder includes receiving a coded video bitstream that includes one or more 2D meshes corresponding to a 3D mesh. The method includes reconstructing one or more boundary vertices of each of the one or more 2D meshes. The method includes determining whether a reconstruction mode for reconstructing one or more internal vertices of each of the one or more 2D meshes is one of (i) a sampling mode and a (ii) non-sampling mode. The method includes reconstructing the one or more internal vertices of each of the one or more 2D meshes based on the determined reconstruction mode. The method further includes reconstructing the 3D mesh based on the reconstructed one or more boundary vertices of each of the one or more 2D meshes and the reconstructed one or more internal vertices of each of the one or more 2D meshes.

Abstract: A method performed in a decoder includes receiving a coded video bitstream that includes (i) one or more two dimensional (2D) meshes corresponding to a three dimensional (3D) mesh and (ii) a 2D to 3D index array that maps each vertex in the one or more 2D meshes to a respective vertex in the 3D mesh. The method further includes reconstructing the 3D mesh using the 2D to 3D index array to map each vertex in the one or more 2D meshes to the respective vertex in the 3D mesh. The 2D to 3D index array encoded in a tuple format in which each tuple in the 2D to 3D index array includes a first parameter that specifies a starting index of a run, a second parameter that specifies a length of the run, and a third parameter that specifies a direction of the run.

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: An apparatus for image/video encoding includes processing circuitry. The processing circuitry performs, based on one or more input images, respective online training based encoder tunings on a plurality of neural image compression (NIC) frameworks. An online training based encoder tuning on an NIC framework in the plurality of NIC frameworks determines an update to an encoder of the NIC framework with a decoder of the NIC framework having fixed parameters. The processing circuitry selects a first NIC framework based on respective performances of the plurality of NIC frameworks with updated encoders from the online training based encoder tunings. The first NIC framework has a first updated encoder from the online training based encoder tunings. The processing circuitry encodes, by the first updated encoder, the one or more input images, into a coded bitstream and includes a signal indicative of the first NIC framework in the coded bitstream.

Abstract: Neural network based image compression using an optimized end-to-end (E2E) neural image compression (NIC) framework being performed by at least one processor and includes receiving an input image to an E2E NIC framework, processing the input image in its entirety using an encoder in the E2E NIC framework to obtain a first bitstream representation of the input image in its entirety, reconstructing an output image from the first bitstream representation of the input image in its entirety using a decoder in the E2E NIC framework, optimizing the encoder in the E2E NIC framework by reducing a distortion loss between the input image and the output image, and processing the input image using the optimized encoder in the E2E NIC framework to obtain a second bitstream representation of the input image. Further, the input may be partitioned into blocks for which encoder optimization is performed for each block and each block is encoded instead of the entire image.

Abstract: In some examples, an apparatus for image/video processing includes processing circuitry. The processing circuitry determines, from a coded bitstream that carries a compressed image, a value of a parameter for tuning a compression rate of the compressed image. The compressed image is generated by a neural network based encoder according to the value of the parameter. The processing circuitry inputs the value of the parameter to a multi-rate compression domain computer vision task decoder, the multi-rate compression domain computer vision task decoder includes one or more neural networks for performing a computer vision task from compressed images according to corresponding values of the parameter that are used for generating the compressed images. The multi-rate compression domain computer vision task decoder generates a computer vision task result according to the compressed image in the coded bitstream and the value of the parameter.

Abstract: A method and apparatus that receives a coded video bitstream from an encoder; retrieves, from the coded video bitstream, a mesh including a plurality of polygons that describe a surface of a volumetric object; triangulates one or more vertices of the mesh, the one or more vertices are located on a boundary of the mesh or interior of the mesh; infers connectivity information between the one or more vertices using the triangulation of the one or more vertices; and reconstructs one or more boundary UV coordinates based on the connectivity information.

Abstract: Method, apparatus, and system for atlas sampling-based dynamic mesh compression are provided. The process may include receiving a mesh frame with polygons representing a surface of an object; determining that the mesh frame is associated with an irregular UV chart in response to one or more singularity components in the mesh frame; performing boundary detection to the UV chart to identify one or more boundary loops in the UV chart; and compressing information of the identified one or more boundary loops into a bitstream.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes processing circuitry that decodes prediction information for a current block in a current coded picture that is part of a coded video sequence. The prediction information indicates a fractional motion vector for the current block. The processing circuitry determines whether one of a block width and a block height of the current block is below a first threshold. The processing circuitry selects one of an integer motion vector, a first interpolation filter, and a second interpolation filter for the current block when the one of the block width and the block height of the current block is determined to be below the first threshold. The processing circuitry reconstructs the current block based on the selected one of the integer motion vector, the first interpolation filter, and the second interpolation filter.

Abstract: Aspects of the disclosure provide a method and an apparatus including processing circuitry for video decoding. The processing circuitry can decode coding information for a plurality of blocks from a coded video bitstream. The coding information can indicate a high-level control flag for the plurality of blocks. The high-level control flag can indicate whether a plurality of coding tools is disabled for at least one of the plurality of blocks where at least one of the plurality of blocks includes a current block. The processing circuitry can determine whether the plurality of coding tools is disabled for the at least one of the plurality of blocks based on the high-level control flag. The processing circuitry can reconstruct the current block without the plurality of coding tools based on the plurality of coding tools being determined as disabled.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes a processor that is configured to decode prediction information of a current block in a current coding tree unit (CTU) from a coded video bitstream. The prediction information is indicative of an intra block copy mode. The processor is configured to determine a search range for the intra block copy mode based on a size of the current CTU, and determine a block vector that points to a reference block in a same picture as the current block and within the determined search range, the reference block having reconstructed samples buffered in a reference sample memory. Further, the processor is configured to reconstruct at least a sample of the current block based on the reconstructed samples of the reference block that are retrieved from the reference sample memory.

Abstract: This disclosure relates generally to video coding and particularly to video file encapsulation and parameter signaling. For example, a method is disclosed for processing video data which may include receiving a bitstream comprising at least one video sample, the at least one video sample comprising a current video sample and a previous video sample, wherein each video sample comprises at least one video frame, and wherein each video sample is associated with a serving SPS for decoding the each of the at least one video sample; determining the serving SPS for the current video sample as being one of: a previous SPS already parsed from the bitstream and used for decoding the previous video sample; a current SPS encapsulated in the current video sample; and an SPS in a list of candidate SPSs; and decoding the current video sample based on the serving SPS for the current video sample.

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.