Abstract: An intra prediction mode encoding and decoding method, an image decoding device, and an image encoding device operate by deriving most probable modes (MPMs) from surrounding prediction units adjacent to a current prediction unit and deriving an intra prediction mode of the current prediction unit on the basis of an MPM flag indicating whether an MPM having the same prediction mode as the intra prediction mode of the current prediction unit exists among the derived MPMs.

Abstract: A method of video coding at a video coding device includes performing a deformable convolution through a deformable convolutional deep neural network (DNN) to generate one or more first feature maps based on a set of one or more previously reconstructed reference frames, generating a predicted frame based on the one or more first feature maps, and reconstructing a current frame based on the predicted frame. In an embodiment, a set of one or more second feature maps corresponding to the one or more previously reconstructed reference frames can be generated based on a feature extraction DNN. One or more offset maps corresponding to the one or more second feature maps can be generated, respectively, using an offset generation DNN.

Abstract: The present invention relates to an image encoding/decoding method and apparatus. The image decoding method according to the present invention may comprise constructing N MPM lists for a current block, wherein N is equal to or greater than 1, deriving an intra prediction mode of the current block based on the N MPM lists, and performing intra prediction for the current block based on the intra prediction mode.

Abstract: The present invention relates to efficient signaling of an intra prediction mode for predicting a current block in intra prediction coding. According to an aspect of the present invention, a video encoding apparatus divides dozens of intra modes into groups, selects a group to which an actual intra mode of the current block to be encoded belongs, and signals a value corresponding to the group. The video decoding apparatus acquires information on the group to which the actual intra mode of the current block belongs from a bit-stream and then evaluates intra modes belonging to the group to select a final intra mode.

Abstract: A Local illumination compensation system for video encoding and decoding uses memory for storing illumination compensation parameters and does not require access to reconstructed pixels of neighboring blocks. A set of illumination compensation parameters is stored in a dedicated buffer, which is of limited size, and which is decoupled from the coding unit level storage of information. The buffer contains a set of illumination compensation parameters, which may be, for example, computed (or determined in some other manner) on the fly or determined beforehand (for example for example obtained from the video signal or from a device).

Abstract: Video codec for supporting temporal inter-prediction, configured to perform padding of an area of a referenced portion of a reference picture which extends beyond a border of the reference picture, which referenced portion is referenced by an inter predicted block of a current picture by selecting one of a plurality of intra-prediction modes, and padding the area using the selected intra-prediction mode.

Abstract: An image decoding method performed by a decoding device according to the present document comprises: a step for deriving the number of samples of upper peripheral chroma samples and left peripheral chroma samples of a current chroma block on the basis of a specific value and the width and height of the current chroma block; a step for deriving said number of upper peripheral chroma samples and said number of left peripheral chroma samples; and a step for deriving CCLM parameters on the basis of the upper peripheral chroma samples, the left peripheral chroma samples, and down-sampled peripheral luma samples, wherein, when the specific value is derived as 2 and the width and the height of the current chroma block are larger than the specific value, the number of samples is derived as the specific value.

Abstract: A method for video processing is provided. The method includes determining, for a conversion between a current video block of a video that is a chroma block and a coded representation of the video, multiple sets of parameters, wherein each set of parameters defines a cross-component linear model (CCLM) and is derived from a corresponding group of chroma samples at corresponding chroma sample positions; determining, based on the multiple sets of parameters, parameters for a final CCLM; and performing the conversion based on the final CCLM.

Abstract: This disclosure describes filtering techniques applied by an encoder and a decoder during the prediction stage of a video encoding and/or decoding process. The filtering techniques may enhance the accuracy of predictive data used during fractional interpolation, and may improve predictive data of integer blocks of pixels. There are several aspects to this disclosure, including a useful twelve-pixel filter support that may be used for interpolation, techniques that use coefficient symmetry and pixel symmetry to reduce the amount of data needed to be sent between an encoder and a decoder to configure the filter support for interpolation, and techniques for filtering data at integer pixel locations in a manner that is similar to sub-pixel interpolation. Other aspects of this disclosure concern techniques for encoding information in the bitstream to convey the type of filter used, and possibly the filter coefficients used. Predictive coding of filter coefficients is also described.

Abstract: Different implementations are described, particularly implementations for video encoding and decoding using motion compensation with bi-prediction are presented. The encoding method comprises for a picture, obtaining a first predictor for a block of the picture using a first reference picture; obtaining a second predictor for said block of the picture using a second reference picture; using the first predictor and the second predictor for forming a third predictor for the block in bi-prediction inter prediction, wherein the third predictor is obtained as a weighted average of the first predictor and the second predictor; and wherein a weight used in the weighed prediction depend on the position of the sample in the block. Others embodiments are presented for implementing block triangle partition prediction, for implementing block partition prediction using multiple patterns and for corresponding motion compensation in decoding method.

Abstract: An image processing device for performing a data decompression is provided. The image processing device includes a decoder circuit having a plurality of stages for decompressing compressed image data of a plurality of pixels. The decoder circuit is configured to divide the pixels into a plurality of groups. The first stage performs prediction compensation on the compressed image data of a first pixel of the first group at a first time to generate first prediction data, and performs the prediction compensation on the compressed image data of a second pixel of the first group at a second time using the first prediction data. The second stage performs the prediction compensation on the compressed image data of a first pixel of the second group at the second time using the first prediction data, to generate second prediction data.

Abstract: An intra prediction method and a device using the intra prediction method are provided. The intra prediction method includes the steps of: deriving a current prediction mode as a prediction mode of a current block; constructing neighboring samples of the current block with available reference samples; filtering the available reference samples; and generating predicted samples of the current block on the basis of the filtered available reference samples. The filtering step includes performing the filtering using the available reference sample located in the prediction direction of the current prediction mode and a predetermined number of available reference samples neighboring to the prediction direction of the current prediction mode.

Abstract: A method comprising: encoding at least four bitstream versions of a same content divided into segments of independently coded tile sets representing a plurality of spatial regions, wherein a first and a second bitstream comprise independently coded tile sets encoded at a first quality, and a third and a fourth bitstream comprise independently coded tile sets encoded at a second quality, wherein the first and the third bitstream have first random access picture interval and the second and the fourth bitstream have second random access picture interval, which is an integer multiple of the first random access picture interval; grouping the independently coded tile sets of all four bitstreams representing a common spatial region into a plurality of groups of collocated sub-picture tracks, wherein only one of said tile sets per group is intended to be received and/or decoded per any segment; and generating at least one instruction for merging tile sets of different spatial locations into at least one coded picture

Abstract: The present disclosure provides methods for picture processing. The method can include: receiving a bitstream comprising a set of pictures; determining, according to the received bitstream, whether a virtual boundary is signaled at a sequence level for the set of pictures; in response to the virtual boundary being signaled at the sequence level, determining a position of the virtual boundary for the set of pictures, the position being bounded by a range signaled in the received bitstream; and disabling in-loop filtering operations across the virtual boundary.

Abstract: Aspects of the disclosure provide methods and apparatus for video decoding. Processing circuitry of the apparatus decodes coded information for a reconstructed sample of a current component in a current picture from a coded video bitstream. The coded information indicates a sample offset filter to be applied to the reconstructed sample. A filter shape of the sample offset filter is one of a plurality of filter shapes. Each of the plurality of filter shapes includes first reconstructed samples of a first component in the current picture. A filtered sample value of the reconstructed sample is determined based on the first reconstructed samples in the filter shape. The sample offset filter is an in-loop filter by which the output value is applied to the reconstructed sample as an offset to filter out coding artifacts while retaining details of the current component in the current picture.

Abstract: An method of decoding video data includes deriving, for a current block of video data and using decoder side intra mode derivation (DIMD), a list of intra modes using reconstructed samples of neighboring blocks; constructing, for the current block, a most probable mode (MPM) list, wherein constructing the MPM list comprises inserting, into the MPM list, at least one intra mode from the derived list of intra modes; and predicting, using a candidate selected from the constructed MPM list, the current block.

Abstract: Devices, systems and methods for coefficient coding in transform skip mode are described. An exemplary method for visual media processing includes: for encoding a current video block in a video region of a visual media data into a bitstream representation of the visual media data, identifying usage of a coding mode and/or an intra prediction mode and/or a set of allowable intra prediction modes; and upon identifying the usage, making a decision of whether to include or exclude, in the bitstream representation, a syntax element indicative of selectively applying a transform skip mode to the current video block, wherein, in the transform skip mode, a residual of a prediction error between the current video block and a reference video block is represented in the bitstream representation of the visual media data without applying a transformation.

Abstract: Methods and systems for reducing banding artifacts when displaying images are described. Identified image bands are filtered using an adaptive sparse finite response filter, where the tap-distance in the sparse filter is adapted according to an estimated width of each image band. Image debanding may be performed across multiple pixel orientations, such as rows, columns, a 45-degree angle, or a ?45-degree angle. Given a threshold to decide whether sparse filtering needs to be performed or not, an iterative debanding process is also proposed.

Abstract: A method of video processing is described. The method includes: determining, based on a coding mode of a current video block of a video, whether a position dependent intra prediction combination (PDPC) method is used for coding the current video block based on a first rule, and performing a conversion between the current video block and a coded representation of the video according to the determining, wherein the PDPC method combines neighboring samples with a prediction signal of the current video block to generate a refined prediction signal of the current video block.

Abstract: A method of decoding JVET video, comprising defining a coding unit (CU) template within a decoded area of a video frame, the CU template being positioned above and/or to the left of a current decoding position for which data was intra predicted, defining a search window within the decoded area, the search window being adjacent to the CU template, generating a plurality of candidate prediction templates based on pixel values in the search window, each of the plurality of candidate prediction templates being generated using different intra prediction modes, calculating a matching cost between the CU template and each of the plurality of candidate prediction templates, selecting an intra prediction mode that generated the candidate prediction template that had the lowest matching cost relative to the CU template, and generating a prediction CU for the current decoding position based on the intra prediction mode.

Abstract: Devices, systems and methods for sub-block based prediction are described. In a representative aspect, a method for video processing includes partitioning a first component of a current video block into a first set of sub-blocks and partitioning a second component of the current video block into a second set of sub-blocks. A sub-block of the second component corresponds to one or more sub-blocks of the first component. The method also includes deriving, based on a color format of the current video block, motion vectors for a sub-block of the second component based on motion vectors for one or more corresponding sub-blocks of the first color component.

Abstract: The present invention relates to a technique for encoding and decoding video data, and more particularly, to a method for performing inter-prediction in an effective manner. The present invention combines an inter-prediction method using an AMVP mode and an inter-prediction method using a merge mode so as to propose a method for using the same candidate. The method for encoding video data proposed by the present invention comprises the following steps: receiving mode information on an inter-prediction method of a current block; determining, on the basis of the received mode information, whether the interprediction method to be applied to the current block is an AMVP mode or a merge mode; and selecting a candidate to derive motion information of the current block, wherein the candidate is selected in a left region, top region and corner region of the current block and in the same position block as the current block, and the AMVP mode and the merge mode are applied on the basis of the selected candidate.

Abstract: In a moving image decoding device for decoding encoded data of a tile group splitting a picture into one or more rectangular regions and consisting of one or more segments, a WPP enabled flag for indicating whether a segment in an object tile group is a CTU row having a height of one CTU is decoded, and when the WPP enabled flag is 1, after a CTU at a right end of the CTU row is decoded, an end bit of a first segment having a fixed value is decoded.

Abstract: An image processing apparatus including a memory and a processor is provided. The image processing apparatus is configured to perform selecting one of data compression processing modes in response to a user input, and executing, according to the selected data compression processing mode, data compression processing on an input captured image based on an inter-frame prediction. The image processing apparatus is further configured perform generating a compressed image from the executed data compression processing. A group of pictures with respect to the generated compressed image is different according to the data compression processing modes. When receiving a request for acquiring vital information from a person captured in the input captured image, one of the data compression processing modes is selected so that the generated compressed image is configured by I pictures only.

Abstract: An image decoding method performed by a decoding device according to the present disclosure comprises: a step of deriving reference picture list 0 (L0) and reference picture list 1 (L1); a step of deriving two motion vectors (MV) for a current block, the two MVs including MVL0 for the L0 and MVL1 for the L1; a step of determining whether to apply bi-prediction optical flow (BIO) prediction for deriving refined motion vectors by sub-blocks to the current block; a step of deriving a refined motion vector for a sub-block of the current block based on the MVL0 and MVL1, if the BIO prediction is applied to the current block; and a step of deriving a prediction sample based on the refined motion vector.

Abstract: A video processing method includes determining, for a conversion between a block of a video and a bitstream representation of the video, that a secondary transform with a reduced dimension dimension (e.g., an inverse low frequency non-separable transform) is applicable to a single sub-block of the block in case a dimension of the block satisfies a condition. The secondary transform is performed between a forward primary transform and a quantization step or between a de-quantization step and an inverse primary transform. The reduced dimension is reduced from a dimension of the block. The method also includes performing the conversion based on the determining.

Abstract: A method of dividing an input image signal into pixel blocks, and performing inter-prediction on the divided pixel blocks. This method includes selecting predicted motion information from a motion information buffer storing motion information in an encoded region, and predicting motion information of an encoding target block by using the predicted motion information. The method further includes acquiring representative motion information from a plurality of items of motion information in an encoded region in accordance with first information indicating a method of selecting the predicted motion information, thereby obtaining only the representative motion information.

Abstract: An intra predictor (181) for performing intra prediction on each of blocks obtained by dividing an original image in the form of a frame, the intra predictor (181) includes; a linear model calculator (1811a) configured to calculate a linear model of the luminance component and the chroma component of the target block using decoded pixel values of the luminance component and decoded pixel values of the chroma component around the target block on which the intra prediction is performed; a chroma component predictor (1811b) configured to predict pixel values of the chroma component of the target block by applying the linear model calculated by the linear model calculator (1811a) to decoded pixel values of a luminance component of the target block; and a chroma component corrector (1812) configured to correct predicted pixel values of the chroma component obtained by the chroma component predictor (1811b) using decoded pixel values that were not used to calculate a linear model by the linear model calculator (181

Abstract: According to the present invention, provided is a method of processing a video signal, the method including: obtaining a transform coefficient of a current block from a bitstream according to a predetermined scanning order; determining an intra prediction mode of the current block on the basis of the transform coefficient; and performing intra prediction on the current block using the intra prediction mode and a neighboring sample adjacent to the current block.

Abstract: Particular embodiments provide a variable, BitDepth, that may be set at a value based on a number of bits used to represent pixels in pictures of a video. The variable may be used in syntax elements in HEVC, such as the HEVC range extension, but other coding standards may be used. By using the variable, different resolutions for the video may be accommodated during the encoding and decoding process. For example, the number of pixels in the pictures may be represented by 8 bits, 10 bits, 12 bits, or another number of bits depending on the resolution. Using the BitDepth variable in the syntax provides flexibility in the motion estimation and motion compensation process. For example, syntax elements used in the weighted prediction process may take into account different numbers of bits used to represent the pictures.

Abstract: A method for video processing is provided. The method includes determining, for a conversion between a current video block of a video that is a chroma block and a coded representation of the video, multiple sets of parameters, wherein each set of parameters defines a cross-component linear model (CCLM) and is derived from a corresponding group of chroma samples at corresponding chroma sample positions; determining, based on the multiple sets of parameters, parameters for a final CCLM; and performing the conversion based on the final CCLM.

Abstract: Devices, systems and methods for digital video coding, which include sub-block based inter prediction methods, are described. An exemplary method for video processing includes determining, for a conversion between a current block of video and a bitstream representation of the video, a maximum number of candidates in a sub-block based merge candidate list and/or whether to add sub-block based temporal motion vector prediction (SbTMVP) candidates to the sub-block based merge candidate list based on whether temporal motion vector prediction (TMVP) is enabled for use during the conversion or whether a current picture referencing (CPR) coding mode is used for the conversion, and performing, based on the determining, the conversion.

Abstract: A video encoder and video decoder may be configured to disable subpicture processing in situations where reference picture scaling is enabled. In another example, when reference picture scaling is enabled, a video encoder may determine a reference picture scaling ratio for the reference picture resampling process based on a width of a scaling window (PicOutputWidthL) of the current picture and a height of the scaling window (PicOutputHeightL) of the current picture. The values of PicOutputWidthL and PicOutputHeightL are constrained, respectively, relative to a width of a scaling window (refPicOutputWidthL) of the reference picture and a height of the scaling window (refPicOutputHeightL) of the reference picture.

Abstract: An image decoding method according to the present disclosure includes deriving a history-based motion vector prediction (HMVP) buffer for a current block, deriving motion information of the current block based on an HMVP candidate included in the HMVP buffer, generating prediction samples for the current block based on the motion information, and generating reconstructed samples based on the prediction samples, and the HMVP buffer is initialized when processing a first-ordered CTU in a CTU row in which a current CTU is located, and the current block is included in the current CTU.

Abstract: To apply a filter to input image data in accordance with an image characteristic. A CNN filter includes a neural network configured to receive an input of one or multiple first type input image data and one or multiple second type input image data, and output one or multiple first type output image data, the one or multiple first type input image data each having a pixel value of a luminance or chrominance, the one or multiple second type input image data each having a pixel value of a value corresponding to a reference parameter for generating a prediction image and a differential image, the one or multiple first type output image data each having a pixel value of a luminance or chrominance.

Abstract: A computing device performs a method of decoding video data by reconstructing a luma block corresponding to a chroma block; searching a sub-group of a plurality of reconstructed neighboring luma samples in a predefined order to identify a maximum luma sample and a minimum luma sample; computing a down-sampled maximum luma sample corresponding to the maximum luma sample; computing a down-sampled minimum luma sample corresponding to the minimum luma sample; generating a linear model using the down-sampled maximum luma sample, the down-sampled minimum luma sample, the first reconstructed chroma sample, and the second reconstructed chroma sample; computing down-sampled luma samples from luma samples of the reconstructed luma block, wherein each down-sampled luma sample corresponds to a chroma sample of the chroma block; and predicting chroma samples of the chroma block by applying the liner model to the corresponding down-sampled luma samples.

Abstract: Embodiments of the present disclosure provide a method and device for processing a video signal. A method for decoding an image signal according to an embodiment of the present disclosure comprises the steps of: determining a non-separable transform set index indicating a non-separable transform set used for a non-separable transform of a current block from among non-separable transform sets predefined on the basis of an intra-prediction mode of the current block; determining. as a non-separable transform matrix, a transform kernel indicated by a non-separable transform index for the current block from among transform kernels included in the non-separable transform set indicated by the non-separable transform set index; and applying the non-separable transform matrix to an upper left region which of the current block, which is determined according to the width and height of the current block, wherein each of the predefined non-separable transform sets includes two transform kernels.

Abstract: Innovations in unified intra block copy (“BC”) and inter prediction modes are presented. In some example implementations, bitstream syntax, semantics of syntax elements and many coding/decoding processes for inter prediction mode are reused or slightly modified to enable intra BC prediction for blocks of a frame. For example, to provide intra BC prediction for a current block of a current picture, a motion compensation process applies a motion vector that indicates a displacement within the current picture, with the current picture being used as a reference picture for the motion compensation process. With this unification of syntax, semantics and coding/decoding processes, various coding/decoding tools designed for inter prediction mode, such as advanced motion vector prediction, merge mode and skip mode, can also be applied when intra BC prediction is used, which simplifies implementation of intra BC prediction.

Abstract: Generating, by a processor in response to instructions stored on a non-transitory computer readable medium, a reconstructed frame, may include generating a reconstructed block of the reconstructed frame by decoding from an encoded bitstream. Decoding may include decoding a value from the encoded bitstream, identifying, in accordance with the value, a probability distribution for generating the reconstructed block, wherein the value indicates the probability distribution among a plurality of probability distributions determined independently of generating the reconstructed frame, entropy decoding an encoded prediction mode from the encoded bitstream using the probability distribution to identify a prediction mode for generating the reconstructed block, generating a prediction block in accordance with the prediction mode; combining the prediction block and a reconstructed residual block to obtain the reconstructed block, and including the reconstructed block in the reconstructed frame.

Abstract: An intra prediction method according to the present invention comprises the following steps: performing a directional prediction using at least one of a neighboring pixel of a current block and a left upper corner pixel positioned at a left upper corner of the current block so as to obtain a first prediction value for the current block; obtaining a second prediction value for the current block using the reference sample positioned in the current block; and weighted summing the first prediction value and the second prediction value using a weighting matrix so as to obtain a final prediction value for the current block. According to the present invention, image encoding/decoding efficiency may be improved.

Abstract: A system comprises an encoder configured to compress attribute and/or spatial information for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. To compress the attribute and/or spatial information, the encoder is configured to convert a point cloud into an image based representation. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud. In some embodiments, an encoder applies an attribute transfer function to attributes of an image based representation with out-of-loop smoothing such that a decoder may apply any smoothing filter supported by the decoder without being restricted to using a similar smoothing filter as the encoder.

Abstract: A decoder includes circuitry configured to receive a current block, determine the current block is a block for updating an unavailable reference frame based on the current block, and update the unavailable reference frame using the current block. Related apparatus, systems, techniques, and articles are also described.

Abstract: An image decoding method according to the present disclosure comprises deriving a first candidate intra prediction mode based on a first neighboring block of a current block; deriving a second candidate intra prediction mode based on a second neighboring block of the current block; constructing MPM (Most Probable Mode) list of the current block based on the first candidate intra prediction mode and the second candidate intra prediction mode; deriving an intra prediction mode for the current block based on the MPM list; and generating a prediction sample for the current block based on the intra prediction mode, wherein the first neighboring block is a left neighboring block located at the lowermost side among neighboring blocks adjacent to a left boundary of the current block, and wherein the second neighboring block is an upper neighboring block located at the rightmost side among neighboring blocks adjacent to an upper boundary of the current block.

Abstract: An image decoding apparatus includes: a first filter unit configured to apply a first filter to an image (a luminance image and a chrominance image); a second filter unit configured to apply a second filter to an output image of the first filter; a filter set derivation unit configured to decode a filter coefficient from coded data; and a third filter unit configured to apply a third filter to an output image of the second filter by using the filter coefficient. In a case that the third filter unit performs filter processing for the luminance image by using a luminance output image of the second filter, the third filter unit performs processing of clipping an amount of change of a pixel value through the filter processing within a prescribed range of value.

Abstract: Encoding or decoding a picture part of video information can include using a refinement mode per block where the refinement mode can be based on a refinement parameter. The refinement mode can include a cross-component refinement that can be a cross-component chroma refinement. The refinement mode can include enabling selection per block of a refinement parameter where the refinement parameter can include one or more chroma refinement parameters included in a chroma refinement table.

Abstract: An image decoding method according to the present invention may comprise the steps of: generating a merge candidate list of a current block; selecting one merge candidate from merge candidates included in the merge candidate list; and performing motion compensation of the current block on the basis of motion information of the selected merge candidate.

Abstract: A video encoding device includes a local decode generation unit for generating a reference image based on a result of encoding of a divided image, a compression unit for compressing the reference image to generate a compressed data, a reference image storage determination unit for determining whether to store the compressed data in a memory, and an inter-prediction unit for performing motion vector search for inter-coding based on a reference image stored in the memory. The reference image storage determination unit sets an allowable data amount used for storing the reference image for each determined area of the moving image data, and determines whether or not to store the compressed data obtained by compressing the reference image in the memory based on the allowable data amount. Inter-prediction unit sets the reference image corresponding to the compressed data stored in the memory as the search range of motion vector search.

Abstract: A method for decoding an image by a decoding device, according to the present document, comprises the steps of: acquiring image information; and generating a reconstructed picture on the basis of the image information.

Abstract: Embodiments for volumetric video encoding and decoding relating to one or more three-dimensional objects are disclosed. In encoding, after mapping from 3D space to 2D plane (802) a point in the 2D plane is examined (805) to determine which points of the 3D object are mapped to the same point to obtain a set of candidate points. Candidate points belonging to a same surface can be used to determine a center of mass for the surface (807). A depth value of the centre of mass is mapped to a 2D projection depth plane (808). A colour value for the centre of mass is interpolated from colour values of points of the set of surface points which are nearest neighbours of the center of mass (810), and used as the colour of the surface in the texture plane (812). Corresponding embodiments for decoding are provided.

Abstract: This application provides an example inter prediction method and a related example apparatus. One example method includes parsing a bitstream to determine prediction information of a to-be-processed picture block, where the prediction information indicates that a prediction direction of the to-be-processed picture block is bidirectional prediction, where the bitstream does not include target identification information, and where the target identification information indicates to perform local illumination compensation (LIC) on the to-be-processed picture block; and obtaining a prediction value of the to-be-processed picture block based on the prediction information.