Abstract: A method for video encoding includes determining whether a current block in a picture to be included in a coded video bitstream meets a size requirement and, in response to determining that the current block meets the size requirement, determining an intra block copy prediction mode usage flag for the current block based on a type of a tile group or slice to which the current block belongs. In response to determining that the current block meets the size requirement, the method further includes determining, based on the IBC prediction mode usage flag, an IBC prediction mode that is separate from an inter prediction mode and an intra prediction mode, determining a block vector that points to a reference area in the picture in response to the determination of the IBC prediction mode, and encoding the current block based on reference samples within the reference area in the picture.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to obtain volumetric data of at least one three-dimensional (3D) visual content, derive a mesh from a frame of the volumetric data, the mesh including a plurality of base mesh vertices, determine a displacement of at least one vertex, that is not of the base mesh vertices, based on a series of projections from at least one of the plurality of base mesh vertices that is a neighboring one of the plurality of base mesh vertices to the at least one vertex, predicting the at least one vertex based at least on the determined displacement, and encode the volumetric data based on the predicted at least one vertex.

Abstract: A method and apparatus for encoding or decoding a video sequence includes encoding or decoding the video sequence using a 4:4:4 chroma format, or encoding or decoding the video sequence using a 4:2:2 chroma format, wherein when encoding or decoding the video sequence using the 4:4:4 chroma format, copying an affine motion vector of one 4×4 luma block using an operation other than an averaging operation and associating the affine motion vector to a co-located 4×4 chroma block, and when encoding or decoding the video sequence using the 4:2:2 chroma format, associating each 4×4 chroma block with two 4×4 co-located luma blocks such that an affine motion vector of one 4×4 chroma block is an average of the motion vectors of the two co-located luma blocks.

Abstract: This disclosure relates generally to coding and decoding of 3-dimensional (3D) mesh and specifically to efficient coding of a vertex degree and face degree of 3D polygon mesh. In some implementations, when encoding a face, a vertex of the face following a split vertex of the face may be linked rather than signaled. In some other example implementations, a context for entropy encoding/decoding a vertex in the vertex degree or a face in the face degree may be selected based on cross characteristics in the face degree or the vertex degree.

Abstract: In a method, a position prediction of a current vertex of a base mesh associated with a mesh in a current mesh frame is determined. An attribute prediction of the current vertex is determined. The base mesh includes a subset of a plurality of vertices of the mesh. A position prediction residue for the position prediction of the current vertex is quantized to generate a quantized position prediction residue. An attribute prediction residue for the attribute prediction of the current vertex is quantized to generate a quantized attribute prediction residue. The quantized position prediction residue for the position prediction of the current vertex is entropy coded in a bitstream. The quantized attribute prediction residue for the attribute prediction of the current vertex is entropy coded in the bitstream.

Abstract: This application provides a method and an apparatus for constructing a motion information list in video encoding and decoding and a device, which relates to the field of video encoding and decoding technologies. The method includes: constructing a space domain motion information list, the space domain motion information list including motion information of a space domain neighboring block of a current block, and the space domain neighboring block including at least an intra string copy (ISC) block; and obtaining at least one piece of motion information from the space domain motion information list when motion information in a candidate motion information list is insufficient, and filling the candidate motion information list using the at least one piece of motion information.

Abstract: This application provides a method for constructing a candidate motion information list performed by a computing device. The method includes: obtaining a candidate motion information list for providing one or more candidate prediction displacement vectors for a current coding unit; determining at least one piece of motion information when a length of the candidate motion information list meets a condition, the length referring to a number of pieces of motion information in the candidate motion information list; and adding the at least one piece of motion information to the candidate motion information list to obtain an updated candidate motion information list. By filling a candidate motion information list using extra motion information when existing motion information included in the candidate motion information list is insufficient, more effective displacement vectors are provided in the candidate motion information list to achieve a better displacement vector prediction effect.

Abstract: A video decoding and encoding method and apparatus, a computer-readable medium, and an electronic device. The video decoding method includes classifying decoded blocks adjacent to a target block according to information about the decoded blocks to obtain at least one category, obtaining a category identifier corresponding to the target block based on coding information corresponding to the target block, determining a target category corresponding to the target block from the at least one category according to the category identifier corresponding to the target block, determining a predictive vector of the target block based on vectors of decoded blocks included in the target category, and decoding the target block based on the predictive vector.

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: 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: A method of video decoding performed in a video decoder includes receiving a coded video bitstream including a current block that is divided into a plurality of sub-blocks. Sub-block based affine motion compensation is performed on the current block to generate a sub-block prediction for each pixel in each sub-block of the current block. One or more spatial gradients are determined for each sub-block prediction. For each sub-block prediction, prediction refinement with optical flow process is performed using the respective determined one or more spatial gradients and at least one constraint included in the coded video bitstream. For each sub-block prediction, an output of the respective prediction refinement is added to the respective sub-block prediction to generate a final prediction for each pixel in each sub-block of the current block.

Abstract: Aspects of the disclosure provide a method and an apparatus for video coding. In some examples, the apparatus includes processing circuitry. The processing circuitry determines, for a current block in a current picture, motion information including a first motion vector (MV) that has a x component and a y component. Each of the x and y components has a fractional MV precision that is 2?N of a sample size in the current block and has one of 2L+1 MV values with the fractional MV precision, N being 4 and indicating the fractional MV precision, and a magnitude of the first MV being represented by L bits. At least one sample of the current block is encoded based on the motion information.

Abstract: The present disclosure includes a method, apparatus, and non-transitory computer-readable medium for adaptive neural image compression by meta-learning. The method may include generating a substitute input image and a substitute target quality control parameter using an original input image and a target quality control parameter, wherein the substitute input image is a modified version of the original input image and the substitute target quality control parameter is a modified version of the target quality control parameter. The method may further include encoding the substitute input image, based on the substitute input image and the substitute target quality control parameter, using an encoding neural network, to generate a compressed representation of the substitute input image.

Abstract: Aspects of the disclosure provide a method and an apparatus including processing circuitry for video decoding. The processing circuitry decodes coding information for a current block. The coding information indicates that the current block is coded in a string copy mode and the coding information includes a first syntax element indicating a string length of a current string in the current block. A coded value of the first syntax element indicates a number N3 of sample groups. Each sample group has L samples, N3 and L being positive numbers. The string length and a number M1 of samples in the current block are divisible by L. The processing circuitry determines a string vector (SV) and the string length of the current string in the current block based on the coding information. The processing circuitry reconstructs the current string based on the SV and the string length of the current string.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to obtain, from a bitstream, a mesh representing an encoded volumetric data of at least one three-dimensional (3D) visual content, and decode the encoded volumetric data based on a base mesh quantization of the mesh, and the base mesh quantization includes predicting a current vertex by already coded vertex positions by a multi-parallelogram prediction, quantizing a prediction residue thereof by a quantization step value, and both compressing the quantized prediction residue and reconstructing a position of the current vertex by adding a de-quantized prediction residue of the quantized prediction residue to the multi-parallelogram prediction as a reference for other vertices.

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to obtain, from a bitstream, a mesh representing an encoded volumetric data of at least one three-dimensional (3D) visual content, and decode the encoded volumetric data based on displacement vectors of vertices of the mesh, and the displacement vectors are based on a square root of three subdivision in which faces of the mesh are iteratively subdivided in a manner in which a number of subdivided faces resulting from subdividing the mesh in an iteration is less than four times a number of faces from before subdividing the mesh in the iteration.

Abstract: This disclosure relates to methods and systems for encoding or decoding a 3D mesh with predictive coding of boundary geometry information. The example decoding method includes receiving a coded bitstream comprising a geometry patch for a three-dimension mesh; extracting, from the coded bitstream, a reconstructed geometry image for the geometry patch comprising a set of points corresponding to a set of geometry coordinates for a boundary vertex in the three-dimension mesh; deriving based on the set of the geometry coordinates, a 3D geometry coordinate for the boundary vertex; obtaining a prediction residue for the boundary vertex; and reconstructing, by the device, geometry information of the boundary vertex based on the derived 3D geometry coordinate and the prediction residue.

Abstract: Aspects of the disclosure provide a method and an apparatus including processing circuitry for video decoding. The processing circuitry receives, from a coded video bitstream, coding information for a current picture. At least one flag in the coding information indicates one or more allowable coding types for sub-partitions in the current picture. The one or more allowable coding types include at least one of intra coding and inter coding for the sub-partitions. The processing circuitry determines, based on the at least one flag, whether to decode intra syntax elements used only for coding intra sub-partitions and whether to decode inter syntax elements used only for coding inter sub-partitions. The processing circuitry decodes the intra syntax elements in the coding information when the intra syntax elements are determined to be decoded and decodes the inter syntax elements in the coding information when the inter syntax elements are determined to be decoded.

Abstract: This disclosure relates generally to image processing and specifically to processing panorama images using neural networks to generate depth maps, layouts, semantic maps or the like with reduced distortion and improved continuity. Methods and systems are described for generating such maps by leveraging several essential properties of these panorama images and by using a panorama panel representation and a neural network framework. A panel geometry embedding network is incorporated for encoding both the local and global geometric features of the panels in order to reduce negative impact of panoramic distortion. A local-to-global transformer network is also incorporated for capturing geometric context and aggregating local information within a panel and panel-wise global context.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video encoding includes processing circuitry. The processing circuitry determines whether a current block in a current picture is a small block based on a block size threshold. The processing circuitry constructs a motion vector predictor list for the current block based on whether the current block is the small block, at least one redundancy check with a motion vector candidate in the motion vector predictor list being performed in the construction of the motion vector predictor list based on whether the current block is the small block. The processing circuitry encodes the current block based on the constructed motion vector predictor list.