Abstract: The present invention relates to an image processing method and an apparatus therefor. Specifically, a method for decoding an image may comprise the steps of: decoding a first split flag indicating whether to split a first block using a binary tree structure; when the first split flag indicates that the first block is split, decoding split mode information indicating the direction in which the first block is split; checking whether a second block split from the first block is a square block, according to the split mode information; and when, as a result of the checking, it is determined that the second block is a square block, decoding a second split flag indicating whether to split the second block using a quad tree structure.

Abstract: Methods, apparatus, systems and articles of manufacture to reduce false positive signature matches due to similar media segments in different reference media assets are disclosed. Example apparatus disclosed herein include a signature matcher to compare monitored media signatures with a library of reference media signatures, the monitored media signatures associated with monitored media, the library of reference media signatures including sequences of reference signatures associated with respective reference media assets. Disclosed example apparatus also include a match information identifier to identify a number of different matched reference media assets associated with ones of the sequences of reference media signatures that match a sequence of matched monitored media signatures.

Abstract: The present invention relates to an image encoding/decoding method and apparatus, A method of decoding an image according to an exemplary embodiment of the present invention comprises: decoding transformation information; creating at least one transformed reference picture by applying the transformation information to at least one reference picture organized in a reference picture list; inserting the at least one transformed reference picture into the reference picture list; and performing motion compensation by using the reference picture list.

Abstract: Techniques and tools for performing fading compensation in video processing applications are described. For example, during encoding, a video encoder performs fading compensation using fading parameters comprising a scaling parameter and a shifting parameter on one or more reference images. During decoding, a video decoder performs corresponding fading compensation on the one or more reference images.

Abstract: A method of video processing includes maintaining tables, wherein each table includes a set of motion candidates and each motion candidate is associated with corresponding motion information; and performing a conversion between a first video block and a bitstream representation of a video including the first video block based on at least some of tables, the performing including checking motion candidates in a table in an order defined in a rule until a checking termination criteria is met.

Abstract: A device for coding video data is configured to determine that a current block of video data is coded using an intra prediction mode; add an intra prediction mode of a first neighboring block of the current block to a most probable mode candidate list for the current block; add an intra prediction mode for a second neighboring block of the current block to the most probable mode candidate list for the current block; add an intra prediction mode for a third neighboring block of the current block to the most probable mode candidate list for the current block; and code the current block of video data using an intra prediction mode.

Abstract: Systems, apparatuses, and methods for calculating multi-pass histograms for palette table derivation include an encoder that calculates a first histogram for a first portion of most significant bits (MSBs) of pixel component values of a block of an image or video frame. Then, the encoder selects a given number of the highest pixel count bins from the first histogram. The encoder then increases the granularity of these selected highest pixel count bins by evaluating one or more additional bits from the pixel component values. A second histogram is calculated for the concatenation of the original first portion MSBs from the highest pixel count bins and the one or more additional bits, and the highest pixel count bins are selected from the second histogram. A palette table is derived based on these highest pixel count bins selected from the second histogram, and the block is encoded using the palette table.

Abstract: A method of generating a refined depth map for a three-dimensional (3D) model of an object is described. The method may include may include warping a set of target images, resulting in warped target images, wherein the set of target images is selected from the plurality of images; determining a difference between each warped target image and a reference image, wherein the reference image is from the plurality of images; determining, for each warped target image, an alpha mask comprising per-pixel weights; and updating an initialized depth map based on alpha mask, resulting in the estimated depth map. Related systems, devices and computer program products are also described.

Abstract: A method of increasing temporal resolution: a) provides an original video having a given spatial resolution; b) compresses a first frame of said original video using any image compression method; and c) repeatedly compresses a next frame of said original video using the steps of: i. providing a current video comprising the already compressed video frames, said current video having an initial spatial resolution; ii. repeatedly reducing the spatial resolution of said current video and the spatial resolution of said next frame of the original video, to produce a lowest level spatial resolution current video and a lowest level spatial resolution next frame of the original video; and iii. compressing said lowest level spatial resolution next frame of the original video to produce a lowest level compressed next frame.

Abstract: Methods, apparatus, systems and articles of manufacture to compress data are disclosed.

Abstract: A video decoder can be configured to decode a block of video data by determining a block of video data is coded in an intra prediction mode; determining one or more samples for intra predicting the block of video data, wherein the one or more samples comprise samples that are already reconstructed and not adjacent to the block of video data; and based on the one or more samples, generating a predictive block for the block of video data.

Abstract: A video decoder may determine, based on syntax elements in a bitstream that comprises an encoded representation of the video data, residual quantized samples of a block of the video data. Additionally, the video decoder may determine quantized residual values based on the residual quantized samples. After determining the quantized residual values, the video decoder may inverse quantize the quantized residual values. The video decoder may generate predicted values by performing intra prediction for the block using unfiltered samples from above or left block boundary samples. Furthermore, the video decoder may reconstruct original sample values of the block based on the inverse-quantized quantized residual values and the prediction values.

Abstract: Video data processing methods and apparatuses in a video encoding or decoding system for processing a slice partitioned into Coding Units (CUs). The video encoding or decoding system receives input data of a current CU and checks a size of the current CU. The residual of the current CU is set to zero or the current CU is coded in Skip mode if the size of the current CU is greater than a maximum size threshold value. A CU with zero residual implies coefficient level values in one or more corresponding transform blocks are all zero, complicated transform processing for large size blocks is therefore avoided.

Abstract: Disclosed are a method and apparatus for improving the accuracy of intra-prediction in order to improve encoding and decoding efficiency. The video decoding method may improve the prediction efficiency for the current pixel to be predicted by referring to the degree of variation in surrounding pixels, to thereby effectively decode the bit stream with improved encoding efficiency. In addition, an additional prediction candidate is used to achieve improved accuracy of intra-prediction, and the thus-improved accuracy of intra-prediction may reduce residual components and improve encoding efficiency. Further, an improved planar mode is utilized to achieve improved intra-prediction.

Abstract: A method of decoding a bitstream by an electronic device is provided. An image frame is received from the bitstream, and a block unit is determined from the image frame. A prediction index of the block unit is determined from the bitstream. A plurality of reference mode indices is determined based on a plurality of neighboring blocks of the block unit. The electronic device determines whether the reference mode indices are greater than a specific one of a plurality of non-angular mode indices. When the reference mode indices are greater than the specific non-angular mode index, the electronic device determines whether a difference between the reference mode indices is equal to two. When the difference is equal to two, a prediction mode is selected according to the prediction index and based on a first candidate list. Then, the block unit is reconstructed based on the prediction mode.

Abstract: The coding efficiency and the amount of processing can be further improved in methods that use the correlation between spatial and temporal directions to estimate parameters that are required for predictions. In LM prediction that predicts pixel values of chrominance, based on pixel values of luminance, an index for a filter that downsamples a luminance image is adaptively signalled.

Abstract: An encoder which encodes a current block of a picture includes a processor and memory. Using the memory, the processor: determines whether intra prediction is to be used for the current block; and when it is determined that intra prediction is to be used for the current block, generates first transform coefficients by performing first transform of residual signals of the current block using a first transform basis; quantizes the first transform coefficients when an intra prediction mode for the current block is a determined mode and the first transform basis is different from a determined transform basis; and generates second transform coefficients by performing second transform of the first transform coefficients using a second transform basis, and quantizes the second transform coefficients, when the intra prediction mode for the current block is not the determined mode or when the first transform basis matches the determined transform basis.

Abstract: A method for coding unit partitioning in a video encoder is provided that includes performing intra-prediction on each permitted coding unit (CU) in a CU hierarchy of a largest coding unit (LCU) to determine an intra-prediction coding cost for each permitted CU, storing the intra-prediction coding cost for each intra-predicted CU in memory, and performing inter-prediction, prediction mode selection, and CU partition selection on each permitted CU in the CU hierarchy to determine a CU partitioning for encoding the LCU, wherein the stored intra-prediction coding costs for the CUs are used.

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: A method for constructing a most probable mode (MPM) list for prediction process corresponding to video block is provided. The method includes determining whether a left block of a current coding block is available, in response to determining that the left block of the current coding block is available, adding an intra prediction mode of the left block into an MPM list; determining whether an above block of the current coding block is available, in response to determining that the above block of the current coding block is available, adding an intra prediction mode of the above block into the MPM list; adding an offset to the prediction mode of the left block to obtain a new prediction mode; and adding the above-offset prediction mode into the MPM list when the above-offset prediction mode is not in the MPM list. The MPM list is used to improve coding efficiency.

Abstract: Disclosed is a method for encoding and decoding an image by applying different filtering strength to reference pixels based on a size relationship between a current block and each reference block such that a prediction block for the current block is constructed using reference pixels which are filtered adaptively according to their properties.

Abstract: An apparatus for coding a block of a frame using intra-prediction includes a memory and a processor. The processor is configured to execute instructions stored in the memory to obtain an intra-prediction mode for coding the block of the frame; select a transform type for coding a transform block of a residual block, which results from predicting the block using the intra-prediction mode; and code the transform block using the transform type. To select the transform type includes to, in a case where the intra-prediction mode is a SMOOTH_PRED, select a ADST_ADST transform type; in a case where the intra-prediction mode is a SMOOTH_H_PRED, select a DCT_ADST transform type; and in a case where the intra-prediction mode is a SMOOTH_V_PRED, select a ADST_DCT transform type.

Abstract: Technology is described for decoding a video block. A block-type syntax information is received which indicates a size of a video block in a video frame, wherein a maximum size of the video blocks is 32×32 or 64×64. The video block having the size indicated by the block-type syntax information is received. The video block is partitioned into partitions, and at least one of the partitions is encoded with a first encoding mode and at least one other of the partitions is encoded with a second encoding mode which is different from the first encoding mode. Syntax information is received for the partitions of the video block and for the first encoding mode and the second encoding mode. Motion vector information is received for one or more of the partitions. The video block is decoded based on at least the block-type syntax information and the motion vector information.

Abstract: A method of decoding video data includes determining, by a video decoder implemented in processing circuitry, a context initialization using a plurality of quantization parameters for a portion of a picture of video data decoded using temporal prediction. The method includes storing, by the video decoder, the context initialization with a single probability state for the plurality of quantization parameters. The method includes entropy decoding, by the video decoder, a set of syntax elements in a bitstream using the single probability state.

Abstract: An image encoding/decoding method and apparatus of the present invention may divide one picture into a plurality of division units, determine whether to perform filtering on a boundary of a current division unit based on a predetermined flag, and perform filtering on the boundary of the current division unit in response to the determination.

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 an inter prediction mode with a potential usage of a refinement technique based on a first reference picture and a second reference picture. Then, the processing circuitry determines whether a first equal weighting condition of chroma components from the first reference picture and the second reference picture is satisfied. In response to a failure to satisfy the first equal weighting condition of the chroma components from the first reference picture and the second reference picture, the processing circuitry disables the refinement technique in a reconstruction of a sample in the current block.

Abstract: The present invention provides a method and apparatus for encoding/decoding an image to enhance inter prediction. According to the present invention, the method includes: determining a first reference picture and a second reference picture of a current block; determining both a first reference block in the first reference picture and a second reference block in the second reference picture; partitioning the current block into a plurality of sub blocks; and obtaining a prediction block of each of the sub blocks on the basis of reference candidate block index information of each of the sub blocks.

Abstract: A set of reconstruction elements useable to reconstruct a representation of a signal at a relatively high level of quality using data based on a representation of the signal at a relatively low level of quality is obtained. The representation at the relatively high level of quality is arranged as an array comprising at least first and second rows of signal elements. A reconstruction element is associated with a respective signal element in the set. A set of data elements is derived based on the set of reconstruction elements. At least one of the data elements is derived from at least two reconstruction elements associated with signal elements from the first row and a different number of reconstruction elements associated with signal elements from the second row.

Abstract: The method for decoding an intra-picture prediction mode includes the steps of: determining whether the intra-picture prediction mode of a current prediction unit is identical to a first intra-picture prediction mode candidate or a second intra-picture prediction mode candidate based on bit information; and when the intra-picture prediction mode of the current prediction unit is identical to the first intra-picture prediction mode candidate and/or to the second intra-picture prediction mode candidate, determining whether the first intra-picture prediction mode candidate or the second intra-picture prediction mode candidate is identical to the intra-picture prediction mode of the current prediction unit on the basis of additional bit information, and decoding the intra-picture prediction mode of the current prediction unit.

Abstract: An image processing apparatus processes a first image and a second image so as to detect a corresponding pixel in the second image which corresponds to a target pixel in the first image. The first image has a first parameter value, and the second image has a second parameter value different from the first parameter value. The first parameter value and the second parameter value are values of optical parameters of image capturing systems used to capture the first image and the second image. The image processing apparatus includes an area setter that sets a two-dimensional search area as a partial area in which the corresponding pixel is to be searched in the second image, based on a predetermined range in which each of the first and second parameter values can change, and a detector that detects the corresponding pixel by searching the two-dimensional search area.

Abstract: Techniques for providing selective video forwarding in real-time video applications involving multiple user devices. The techniques can be employed in WebRTC videoconferences, taking into account the heterogeneous natures of device display resolutions and networks in which the respective devices operate. The techniques employ a selective forwarding unit (SFU) having a real-time adaptive video transcoder. The SFU determines whether a benefit to quality of experience (QoE) can be achieved by performing, in real-time, adaptive video transcoding on large video streams produced by the respective devices. If a heterogeneity value associated with available network bandwidths is greater than a predetermined value and sufficient CPU/memory resources are available, then the real-time adaptive video transcoder performs, in real-time, adaptive video transcoding on the large video streams to produce corresponding small video streams, which are selectively forwarded to user devices having low available network bandwidths.

Abstract: A method includes receiving transform coefficients corresponding to a scaled video input signal, the scaled video input signal including a plurality of spatial layers that include a base layer. The method also includes determining a spatial rate factor based on a sample of frames from the scaled video input signal. The spatial rate factor defines a factor for bit rate allocation at each spatial layer of an encoded bit stream formed from the scaled video input signal. The spatial rate factor is represented by a difference between a rate of bits per transform coefficient of the base layer and an average rate of bits per transform coefficient. The method also includes reducing a distortion for the plurality of spatial layers by allocating a bit rate to each spatial layer based on the spatial rate factor and the sample of frames.

Abstract: Techniques for dynamic digital advertising are disclosed. In one particular embodiment, the techniques may be realized as a dynamic advertising method comprising: receiving, by a computer processor associated with a dynamic advertising device, from a client device, first advertising content information including timepoint data for a playback event associated with first advertising content of a first advertising slot on a webpage; configuring, by the computer processor, a recall request for the first advertising content, the recall request including identification data associated with the first advertising content and specifying a timepoint obtained from the timepoint data; receiving, by the computer processor, from the client device, first advertising content resume request; and requesting, by the computer processor, for the client device, using the recall request, timepoint-configured first advertising content having a playback start time equal to the timepoint.

Abstract: Disclosed is technology associated with video encoding and decoding having a structure including one or more layers (quality, spatial, and view) and technology associated with a method that predicts an higher layer signal by using one or more reference layers in encoding and decoding an higher layer. In more detail, an interlayer prediction is capable of being performed by considering a characteristic of each layer by separating a spatial and quality reference layer list constituted by spatial and quality layers to be referred at the same view as a target layer and a view reference layer list constituted by the same spatial and quality layers as a target layer in encoding and decoding encoding and decoding pictures of an higher layer in encoding and decoding encoded and decoded pictures of the higher layer to improve encoding and decoding efficiency.

Abstract: A video encoding method for an electronic device includes: dividing at least one CTU of a video image frame to acquire video prediction units of different sizes; performing initial selection on intra-predicted brightness prediction directions of the video prediction units according to a first rate-distortion-evaluation-function, to obtain a preset number of intra-predicted initially-selected brightness-directions of the video prediction units; performing fine selection on intra-predicted optimal brightness-directions of a related video prediction unit and intra-predicted initially-selected brightness-directions of a video prediction unit of a current size according to a second rate-distortion-evaluation-function, to obtain intra-predicted optimal brightness-directions of the video prediction unit; performing fine selection on intra-predicted chroma prediction directions of the video prediction units according to the second rate-distortion-evaluation-function, to obtain intra-predicted optimal chroma-direction

Abstract: A method of video decoding including receiving a coded video bitstream including a current picture. The method further includes decoding, in a region of the current picture, a plurality of blocks. The method further includes determining whether a predetermined condition associated with the region is met. The method further includes updating a history motion vector predictor (HMVP) buffer in response to a determination that that the predetermined condition is met.

Abstract: Scalable coding concepts are described. One aspect improves parallel decoding of inter-dependent layers of a multi-layer video data stream by introducing a long-term syntax element structure for guaranteeing that during a predetermined time period the pictures of the dependent layer are subdivided so that borders of the spatial segments of the pictures of the second layer and the spatial segments of the first layer overlay. Another aspect concerns upsampling from base layer to enhancement layer. Another aspect introduces a long-term syntax element structure allowing the decoder to determine the inter-layer offset for a predetermined time period. Another aspect introduces a type indicator field changing a way a layer indicator field within the NAL unit headers is to be interpreted. Another aspect allows different codecs/standards to be used for the different layers. Another aspect concerns a syntax element structure which indicates the inter-layer offset in units of the base layer blocks.

Abstract: An image decoding method performed by a decoding apparatus, includes deriving a history-based motion vector prediction (HMVP) buffer for a current block based on a history, and deriving motion information of the current block based on an HMVP candidate included in the HMVP buffer, thereby increasing inter prediction efficiency.

Abstract: Disclosed are a method and apparatus for improving the accuracy of intra-prediction in order to improve encoding and decoding efficiency. The video decoding method may improve the prediction efficiency for the current pixel to be predicted by referring to the degree of variation in surrounding pixels, to thereby effectively decode the bit stream with improved encoding efficiency. In addition, an additional prediction candidate is used to achieve improved accuracy of intra-prediction, and the thus-improved accuracy of intra-prediction may reduce residual components and improve encoding efficiency. Further, an improved planar mode is utilized to achieve improved intra-prediction.

Abstract: A video encoding apparatus may include a partitioning unit which divides a frame included in input video into a plurality of blocks and a rate control module which adjusts a first quantization parameter value of a block corresponding to a region of interest among the plurality of blocks based on a first CBF (current buffer fullness) value of the region of interest, and adjusts a second quantization parameter value of a block corresponding to a non-region of interest among the plurality of blocks based on a second CBF value of the non-region of interest.

Abstract: An inter-prediction method and apparatus uses a reference frame generated based on deep learning. In the inter-prediction method and apparatus, a reference frame is selected, and a virtual reference frame is generated based on the selected reference frame. A reference picture list is configured to include the generated virtual reference frame, and inter prediction for a target block is performed based on the virtual reference frame. The virtual reference frame may be generated based on a deep-learning network architecture, and may be generated based on video interpolation and/or video extrapolation that use the selected reference frame.

Abstract: A method of decoding JVET video includes receiving a bitstream and calculating a final planar prediction in planar mode to predict pixel values for a current coding block. The final planar prediction may rely on using unequal weights applied to each of a horizontal and vertical predictor, where such predictors may be generated by interpolating neighboring pixels for each predicted pixel within a coding block. The computation may be made more accurate by deriving a value for a bottom right neighboring pixel.

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. According to an aspect of the disclosure, the processing circuitry decodes prediction information of a current block in a first coding tree unit (CTU) in a picture from a coded video bitstream. The prediction information is indicative of an intra block copy mode. The processing circuitry excludes reconstructed samples of a second CTU that is adjacent to a left side of the first CTU in the picture from being reference samples for a reconstruction of the current block. Then, the processing circuitry reconstructs samples of the current block based on reference samples that are in the picture and constrained with the exclusion of the reconstructed samples of the second CTU.

Abstract: An image coding method includes: writing, into a sequence parameter set, buffer description defining information for defining a plurality of buffer descriptions; writing, into the sequence parameter set, reference list description defining information for defining a plurality of reference list descriptions corresponding to the buffer descriptions; and writing, into a first header of each processing unit which is included in a coded bitstream, buffer description selecting information for specifying a selected buffer description.

Abstract: A method and apparatus of using logical mode numbers during both prediction and coding in the bit stream, such as for high efficiency video coders (HEVC). These logical intra mode numbers are sorted based on angle which as a result leads to improved coding designs with fewer and smaller look-up tables, and a small gain in coding efficiency. Furthermore, by using this type of naming, the number of most probable modes (MPMs) can be readily extended since no additional tables are required. The use of three MPMs achieves a larger gain of 0.25% and 0.31% for the AI_HE and AI_LC cases, respectively.

Abstract: A method of video decoding at a decoder is disclosed. The method can include receiving a current block in a picture, and determining whether a size of the current block is smaller than or equal to a size threshold. When the size of the current block is smaller than or equal to the size threshold, one or more types of sub-block based merge candidates for decoding the current block can be disabled.

Abstract: A method for decoding a compressed image stream, the image stream having a plurality of frames, each frame consisting of a merged image including pixels from a left image and pixels from a right image. The method involves the steps of receiving each merged image; changing a clock domain from the original input signal to an internal domain; for each merged image, placing at least two adjacent pixels into an input buffer and interpolating an intermediate pixel, for forming a reconstructed left frame and a reconstructed right frame according to provenance of the adjacent pixels; and reconstructing a stereoscopic image stream from the left and right image frames. The invention also teaches a system for decoding a compressed image stream.

Abstract: Innovations in signaling of reference picture list (“RPL”) modification information. For example, a video encoder evaluates a condition that depends at least in part on a variable indicating a number of total reference pictures. Depending on the results of the evaluation, the encoder signals in a bitstream a flag that indicates whether an RPL is modified according to syntax elements explicitly signaled in the bitstream. A video decoder evaluates the condition and, depending on results of the evaluation, parses from a bitstream a flag that indicates whether an RPL is modified according to syntax elements explicitly signaled in the bitstream. The condition can be evaluated as part of processing for an RPL modification structure that includes the flag, or as part of processing for a slice header. The encoder and decoder can also evaluate other conditions that affect syntax elements for list entries of the RPL modification information.

Abstract: A video decoding method performed by a decoding apparatus according to the present disclosure includes deriving one of a plurality of cross-component linear model (CCLM) prediction mode as a CCLM prediction mode of the current chroma block, deriving a sample number of neighboring chroma samples of the current chroma block based on the CCLM prediction mode of the current chroma block, a size of the current chroma block, and a specific value; deriving the neighboring chroma samples of the sample number, calculating CCLM parameters based on the neighboring chroma samples and the down sampled neighboring luma samples, deriving prediction samples for the current chroma block based on the CCLM parameters and the down sampled luma samples and generating reconstructed samples for the current chroma block based on the prediction samples, wherein the specific value is derived as 2.

Abstract: A decoder includes circuitry configured to receive a bit stream, identify, as a function of the bitstream, a current frame, and a cropped sub-frame of the current frame, determine, as a function of the bitstream, a scaling constant associated with the cropped sub-frame, and reconstruct pixel data of the cropped sub-frame using the scaling constant.