Abstract: A method for processing a video includes performing a determination, by a processor, that a first video block is partitioned to include a first prediction portion that is non-rectangular and non-square; adding a first motion vector (MV) prediction candidate associated with the first prediction portion to a motion candidate list associated with the first video block, wherein the first MV prediction candidate is derived from a sub-block MV prediction candidate; and performing further processing of the first video block using the motion candidate list.

Abstract: This disclosure presents a process to generate one or more video frames through guiding the movements of a target object in an environment controlled by physics-based constraints. The target object is guided by the movements of a reference object from a motion capture (MOCAP) video clip. As disturbances, environmental factors, or other physics-based constraints interfere with the target object mimicking the reference object. A tracking agent, along with a corresponding neural network, can be used to compensate and modify the movements of the target object. Should the target object diverge significantly from the reference object, such as falling down, a recovery agent, along with a corresponding neural network, can be used to move the target object back into an approximate alignment with the reference object before resuming the tracking process.

Abstract: Systems and methods for indexing and searching for digital media in a multi-player gaming network are disclosed. In a game module stored locally in each client device, a content editor application generates a user interface through which a player may create, or search for, a personal visual symbol. Search queries are processed to determine asset signatures and, based on the asset signatures, corresponding stored personal visual symbol data are identified.

Abstract: Exemplary video processing methods and apparatuses for coding a current block by overlapped sub-block motion compensation split the current block into overlapped sub-blocks, determine a sub-block MV for each overlapped sub-block, derive an initial predictor for each sub-block by motion compensation using the sub-block MV, derive a final predictor for each overlapped region by blending the initial predictors of the overlapped region, and encode or decode the current block based on the final predictors. Exemplary video processing methods and apparatuses for coding blocks with OBMC generate a converted MV by changing a MV to an integer MV or changing a MV component to an integer component, derive an OBMC region by motion compensation using the converted MVs, and encode or decode the blocks by blending an OBMC predictor with an original predictor.

Abstract: A video decoding device, in the case where a video of the progressive format is inputted, processes a frame as a picture, in the case where a video of the interlace format is inputted, processes a field as a picture. A video decoding device performs display control corresponding to a format of the both video by analyzing display control information in display control information analyzer. The display control information includes sequence unit display control information which is commonly used in a display process of all pictures that belong to a sequence to be decoded and picture unit display control information which is individually used in a display process of a picture to be decoded. A second code string analyzer acquires each of the sequence unit display control information and the picture unit display control information from an extended information area in units of pictures.

Abstract: Pixel values of a current video coding block are intra predicted on the basis of a plurality of reference pixel values. A pixel value of a current pixel is intra predicted on the basis of: a first reference pixel value, wherein the first reference pixel is located in a first neighboring video coding block, a second reference pixel value, wherein the second reference pixel is located in a second neighboring video coding block, a distance between the current pixel and the first reference pixel, and a distance between the current pixel and the second reference pixel.

Abstract: An image decoding method using a merge mode, can include constructing a merge candidate list by using available spatial merge candidates and an available temporal merge candidate; generating a prediction block based on motion information derived by using the merge candidate list; inversely quantizing a quantization block by using a quantization parameter generated per quantization unit, wherein the quantization block is generated with quantization coefficient components; generating a residual block by inversely transforming the inversely quantized quantization block; deriving a reconstructed block by using the prediction block and the residual block, in which the spatial merge candidates are motion information of spatial merge candidate blocks, and the spatial merge candidate blocks are a left block, an above block, an above-right block, a left-below block or an above-left block of a current block, and a reference picture index of the temporal merge candidate is 0.

Abstract: A method of video decoding includes checking one or more video blocks in pre-defined relative positions compared to a first video block to derive a first set of candidates, wherein each of the first set of candidates is derived from corresponding motion information of the video blocks checked, checking, upon a determination that a number of the first set of candidates has not reached a predetermined limit, one or multiple tables to derive a second set of candidates, and processing the first video block based on a bitstream representation of the first video block and the constructed candidate list.

Abstract: A method for dynamically limiting a memory bandwidth of a graphics processing unit (GPU) is applicable to a bandwidth-limited system. The bandwidth-limited system includes an audio/video decoder and a GPU. The method includes detecting a plurality of decoding times of a plurality of frames of an audio/video decoded by an audio/video decoder, and adjusting a max grant amount of a memory bandwidth of a GPU according to the plurality of decoding times of the plurality of frames and a target time. Therefore, in the case where the total memory bandwidth is limited, the memory bandwidth of the GPU is limited by the performance of the corresponding audio/video decoder such that, during audio/video playback, the effect of audio/video playback can be prevented from being affected and at the same time a better graphical user interface can be provided.

Abstract: According to the present invention, an inter prediction method comprises the steps of: generating a merge candidate list for a block to be predicted, wherein the block is to correspond to a current prediction unit; deriving, on the basis of one of a plurality of merge candidates constituting the merge candidate list, motion information on the block to be predicted; and performing, on the basis of the derived motion information, a prediction on the block to be predicted so as to generate a prediction block corresponding to the current prediction unit.

Abstract: A method for processing a video includes performing a determination, by a processor, that a first video block is partitioned to include a first prediction portion that is non-rectangular and non-square; adding a first motion vector (MV) prediction candidate associated with the first prediction portion to a motion candidate list associated with the first video block, wherein the first MV prediction candidate is derived from a sub-block MV prediction candidate; and performing further processing of the first video block using the motion candidate list.

Abstract: Technology for operating a data-source device for assembling a data stream compliant with a data stream constraint. The technology comprises acquiring a plurality of data items by accessing data in a memory and/or transforming data. Prior to completion of the accessing data in a memory, an accessor is selected based on an estimate of access constraint. Prior to completion of the transforming data, a transformer is selected based on an estimate of transformation constraint, wherein the transportation constraint comprises any data acquisition constraint. The access and transformation constraints are dependent upon system state it the data-source system. The data items are positioned in the data stream, and, responsive to achieving compliance with the data stream constraint, the data strewn is communicated.

Abstract: A system and method for compressing video is disclosed, in which video frames that are only between consecutive I-frames are grouped into a video data set. The video data set is split into separate homogeneous files, and each of the homogeneous files are individually compressed. In one embodiment, the individually compressed files are multiplexed to form a bit stream.

Abstract: A method for coding image information includes generating prediction information by predicting information on a current coding unit, and determining whether the information on the current coding unit is the same as the prediction information. When the information on the current coding unit is the same as the prediction information, a flag indicating that the information on the current coding unit is the same as the prediction information is coded and transmitted. When the information on the current coding unit is not the same as the prediction information, a flag indicating that the information on the current coding unit is not the same as the prediction information and the information on the current coding unit are coded and transmitted. At the generating of the prediction information, the prediction information is generated by using the information on the coding unit neighboring to the current coding unit.

Abstract: A method of video decoding includes checking one or more video blocks in pre-defined relative positions compared to a first video block to derive a first set of candidates, wherein each of the first set of candidates is derived from corresponding motion information of the video blocks checked, checking, upon a determination that a number of the first set of candidates has not reached a predetermined limit, one or multiple tables to derive a second set of candidates, and processing the first video block based on a bitstream representation of the first video block and the constructed candidate list.

Abstract: A macro block size determining unit 1 determines the size of each macro block on a frame-by-frame basis. A macro block dividing unit 2 divides an inputted image into macro blocks each having the size determined by the macro block size determining unit 1. A macro block coding unit 3 determines a coding mode for each of the macro blocks divided by the macro block dividing unit 2, and codes pixel values in each of the macro blocks in the determined coding mode.

Abstract: Disclosed is a video signal processing method comprising the steps of: acquiring a merge index which indicates a candidate for prediction of a current block among a plurality of candidates for the prediction of the current block, which are included in a merge candidate list; acquiring motion information of the current block on the basis of motion information corresponding to the candidate indicated by the merge index; when the motion information of the current block includes a plurality of motion vectors corresponding to a list of different reference pictures, comparing picture order count (POC) differences between each of the reference pictures corresponding to the plurality of motion vectors and the current picture including the current block; correcting the plurality of motion vectors on the basis of a result of the comparison; and reconstructing the current block on the basis of the plurality of corrected motion vectors.

Abstract: Overlapped block disparity estimation and compensation is described. Compensating for images with overlapped block disparity compensation (OBDC) involves determining if OBDC is enabled in a video bit stream, and determining if OBDC is enabled for one or more macroblocks that neighbor a first macroblock within the video bit stream. The neighboring macroblocks may be transform coded. If OBDC is enabled in the video bit stream and for the one or more neighboring macroblocks, predictions may be made for a region of the first macroblock that has an edge adjacent with the neighboring macroblocks. OBDC can be causally applied. Disparity compensation parameters or modes may be shared amongst views or layers. A variety of predictions may be used with causally-applied OBDC.

Abstract: An image decoding method includes: dividing a current block into sub-blocks; deriving, for each sub-block, one or more prediction information candidates; obtaining an index; and decoding the current block using the prediction information candidate selected by the index.

Abstract: A method is performed at a computing system having one or more processors and memory. The method includes receiving a first video clip having three or more image frames and computing a first hash pattern, including: (i) computing a temporal sequence of differential frames and (ii) for each differential frame: identifying a respective plurality of feature points and computing a respective hash value that represents spatial positioning of the respective feature points with respect to each other. The method includes receiving a second video clip having three or more image frames and computing a second hash pattern by applying steps (i) and (ii) to the three or more image frames. The method includes computing a distance between the first hash pattern and the second hash pattern and determining that the first and second video clips match when the computed distance is less than a threshold distance.

Abstract: A video coding system may perform inter-layer processing by simultaneously performing inverse tone mapping and color gamut conversion scalability processes on a base layer of a video signal. The video coding system may then perform upsampling on the processed base layer. The processed base layer may be used to code an enhancement layer. Bit depth may be considered for color gamut conversion modules. Luma and/or chroma bit depths may be aligned with respective larger or smaller bit depth values of luma and/or chroma.

Abstract: Method and apparatus of using Pattern-based MV derivation (PMVD), Bi-directional optical flow (BIO) or Decoder-side MV refinement (DMVR) to refine motion for a bi-direction predicted block are disclosed. According to one method of the present invention, a first and a second motion-compensated reference blocks associated with the current block in a first and a second reference pictures from reference picture list 0 and list 1 are determined respectively. The PMVD process, BIO process or DMVR process is applied to generate motion refinement for the current block using reference data corresponding to the first motion-compensated reference block and the second motion-compensated reference block without other reference data outside the first motion-compensated reference block and the second motion-compensated reference block so as to reduce required system memory bandwidth. Also an adaptive block size method for block-based BIO is disclosed.

Abstract: Provided is a method and apparatus for performing intra-prediction using an adaptive filter. The method for performing intra-prediction includes the steps of: determining whether or not to apply a first filter for a reference pixel value on the basis of information of a neighboring block of a current block; applying the first filter for the reference pixel value when it is determined to apply the first filter; performing intra-prediction on the current block on the basis of the reference pixel value; determining whether or not to apply a second filter for a prediction value according to each prediction mode of the current block, which is predicted by the intra-prediction performance on the basis of the information of the neighboring block; and applying the second filter for the prediction value according to each prediction mode of the current block when it is determined to apply the second filter.

Abstract: An embodiment of a motion estimator apparatus may include technology to receive a compound message, and perform rate distortion estimation and check refinement for two or more coding unit descriptions for a source block based on the received compound message. Other embodiments are disclosed and claimed.

Abstract: A method and apparatus for decoding JVET video, including receiving a bitstream, and parsing said bitstream to identify a syntax element indicating an intra direction mode to use for generating at least one predictor. The intra direction mode is a first intra direction mode in a plurality of intra direction modes that includes at least one weighted intra direction mode that corresponds to a non-weighted intra direction mode. The syntax element may identify whether to use a non-weighted or weighted intra direction mode to generate the at least one predictor. Thus, the coding unit may be coded in accordance with the at least one generated predictor associated with the selected intra direction mode.

Abstract: A video coding device may be configured to perform transform data coding according to one or more of the techniques described herein.

Abstract: The present disclosure discloses an image decryption method that includes steps outlined below. Control information in an image stream is read and decrypted. Image stream packets in the image stream are read according to the control information. According to the control information, pixel data of a first reference frame from a first temporary storage block of a memory module and/or of a second reference frame from a second temporary storage block of the memory module are selectively read. A decryption process is performed according to the image stream packets and selectively according to the pixel data of the first and/or the second reference frame to generate pixel data of a decrypted frame. During the decryption process, the pixel data of the decrypted frame is transmitted to a post-processing circuit and is stored to one of the first and the second temporary storage blocks according to the control information.

Abstract: Embodiments of the present disclosure provide a method and a device for processing a picture and an electronic device. The method includes scaling a raw picture to obtain N scaled pictures with different resolutions, where N is a natural number greater than or equal to 2; mapping the N scaled pictures respectively into N content picture each with a same predetermined style feature through a neural algorithm network; scaling the N content pictures to have the same resolution; and encoding and combining the N content images of the same resolution into a dynamic video.

Abstract: A method of video decoding performed in a video decoder includes receiving a coded video bitstream including signaling information for a current block. The method further includes determining block reconstruction information for the current block based on the signaling information. The method further includes reconstructing the current block using the determined block reconstruction information.

Abstract: The present invention provides low complexity planar mode coding in which a value of a bottom-right pixel in a prediction block is calculated from a value of at least one pixel in at least one of an array of horizontal boundary pixels and an array of vertical boundary pixels. Linear and bi-linear interpolations on the value of the bottom-right pixel and values of at least some of the horizontal and vertical boundary pixels to derive values of remaining pixels in the prediction block. A residual between the prediction block and an original block is signaled to a decoder.

Abstract: The present invention provides low complexity planar mode coding in which a first prediction value is calculated using linear interpolation between a value of respective horizontal boundary pixels and a value of one of vertical boundary pixels, and a second prediction value is calculated using linear interpolation between a value of respective vertical boundary pixels and a value of one of the horizontal boundary pixels. The first and second prediction values are then averaged to derive a respective prediction pixel value in a prediction block. A residual between the prediction block and a target block is signaled to a decoder.

Abstract: The present invention relates to a method and device for sharing a candidate list. A method of generating a merging candidate list for a predictive block may include: producing, on the basis of a coding block including a predictive block on which a parallel merging process is performed, at least one of a spatial merging candidate and a temporal merging candidate of the predictive block; and generating a single merging candidate list for the coding block on the basis of the produced merging candidate. Thus, it is possible to increase processing speeds for coding and decoding by performing inter-picture prediction in parallel on a plurality of predictive blocks.

Abstract: The present invention provides low complexity planar mode coding in which a value of a bottom-right pixel in a prediction block is calculated from a value of at least one pixel in at least one of an array of horizontal boundary pixels and an array of vertical boundary pixels. Linear and bi-linear interpolations on the value of the bottom-right pixel and values of at least some of the horizontal and vertical boundary pixels to derive values of remaining pixels in the prediction block. A residual between the prediction block and an original block is signaled to a decoder.

Abstract: A method for decoding a coded video sequence includes decoding at least one tile which comprises a first tile boundary defined by a first tile layout and a second tile boundary defined by second tile layout, wherein the coded video sequence indicates that at least one first prediction mechanism is available across the first tile boundary, and that the at least one first prediction mechanism is not available across the second tile boundary.

Abstract: The present invention provides low complexity planar mode coding in which a value of a bottom-right pixel in a prediction block is calculated from a value of at least one pixel in at least one of an array of horizontal boundary pixels and an array of vertical boundary pixels. Linear and bi-linear interpolations on the value of the bottom-right pixel and values of at least some of the horizontal and vertical boundary pixels to derive values of remaining pixels in the prediction block. A residual between the prediction block and an original block is signaled to a decoder.

Abstract: A non-transitory recording medium is provided that is reproduced by a playback device having an attribute reader, a decoder, and an outputter. The recording medium has recorded therein a video stream that is encoded video information, and a management information file correlated with the video stream. The management information file includes first attribute information, indicating whether a dynamic range of luminance of the video stream is a first dynamic range or a second dynamic range that is wider than the first dynamic range. In a case where the first attribute information indicates the second dynamic range, the first attribute information also indicates a type of the second dynamic range.

Abstract: In omnidirectional videos, only some intra prediction directions may be relevant for intra prediction. For example, for a video generated from an equi-rectangular mapping, only the horizontal directions may be relevant for intra prediction around the poles. To improve compression efficiency, we propose to reduce the number of possible directions, based on the location of the block to be encoded or decoded in the frame. In various embodiments, we may adapt the derivation of the MPM in order to take into account the reduction of intra directions depending on geometric distortions. The encoding method can also be adapted to reduce the number of modes to estimate for a block in omnidirectional videos. The coding of the syntax elements representing the intra direction can also be improved.

Abstract: The present invention provides low complexity planar mode coding in which a value of a bottom-right pixel in a prediction block is calculated from a value of at least one pixel in at least one of an array of horizontal boundary pixels and an array of vertical boundary pixels. Linear and bi-linear interpolations on the value of the bottom-right pixel and values of at least some of the horizontal and vertical boundary pixels to derive values of remaining pixels in the prediction block. A residual between the prediction block and an original block is signaled to a decoder.

Abstract: A behavioral recognition system may include both a computer vision engine and a machine learning engine configured to observe and learn patterns of behavior in video data. Certain embodiments may provide image stabilization of a video stream obtained from a camera. An image stabilization module in the behavioral recognition system obtains a reference image from the video stream. The image stabilization module identifies alignment regions within the reference image based on the regions of the image that are dense with features. Upon determining that the tracked features of a current image is out of alignment with the reference image, the image stabilization module uses the most feature dense alignment region to estimate an affine transformation matrix to apply to the entire current image to warp the image into proper alignment.

Abstract: Techniques related to video coding with context decoding and reconstruction bypass.

Abstract: Provided are an inter prediction method and a motion compensation method. The inter prediction method includes: performing inter prediction on a current image by using a long-term reference image stored in a decoded picture buffer; determining residual data and a motion vector of the current image generated via the inter prediction; and determining least significant bit (LSB) information as a long-term reference index indicating the long-term reference image by dividing picture order count (POC) information of the long-term reference image into most significant bit (MSB) information and the LSB information.

Abstract: The present invention provides low complexity planar mode coding in which a value of a bottom-right pixel in a prediction block is calculated from a value of at least one pixel in at least one of an array of horizontal boundary pixels and an array of vertical boundary pixels. Linear and bi-linear interpolations on the value of the bottom-right pixel and values of at least some of the horizontal and vertical boundary pixels to derive values of remaining pixels in the prediction block. A residual between the prediction block and an original block is signaled to a decoder.

Abstract: The present invention relates to a method and device for sharing a candidate list. A method of generating a merging candidate list for a predictive block may include: producing, on the basis of a coding block including a predictive block on which a parallel merging process is performed, at least one of a spatial merging candidate and a temporal merging candidate of the predictive block; and generating a single merging candidate list for the coding block on the basis of the produced merging candidate. Thus, it is possible to increase processing speeds for coding and decoding by performing inter-picture prediction in parallel on a plurality of predictive blocks.

Abstract: The present invention provides low complexity planar mode coding in which a value of a bottom-right pixel in a prediction block is calculated from a value of at least one pixel in at least one of an array of horizontal boundary pixels and an array of vertical boundary pixels. Linear and bi-linear interpolations on the value of the bottom-right pixel and values of at least some of the horizontal and vertical boundary pixels to derive values of remaining pixels in the prediction block. A residual between the prediction block and an original block is signaled to a decoder.

Abstract: A method of generating a prediction for an area of video data, comprises Receiving a rectangular video block including sample values, and for each sample included in the video block, generating a predictive sample value by averaging a horizontal interpolation and a vertical interpolation corresponding to the location of the sample within the video block.

Abstract: A process for determining the selection of filters and input samples is provided for scalable video coding. The process provides for re-sampling using video data obtained from an encoder or decoder process of a base layer (BL) in a multi-layer system to improve quality in Scalable High Efficiency Video Coding (SHVC). In order to provide better alignment between layers, it is proposed that reference layer offset adjustment parameters be signaled.

Abstract: System, method and products for monitoring media displayed by third-party components. A runtime component monitors execution of a program on the user device. The runtime component identifies an attempt by a third-party component that is integrated with the program to display media. The runtime component obtains obtain data associated with the media, determines a fingerprint of the media and transmits to a server the data and the fingerprint. In response to a request received from the server or lack thereof, the runtime component determines whether to drop the media or transmit the media to the server. The server is provided with aggregated data about different medias displayed by third-party components by different instances of the program executed by different user devices.

Abstract: A video decoder is configured to determine a first motion vector for a first block of video data; perform motion vector refinement on the first motion vector for the first block to determine a refined motion vector for the first block of video data; determine that a second block of video data is coded in a mode that utilizes a motion vector associated with the first block as a motion vector predictor; in response to determining that the second block of video data is coded in the mode that utilizes the motion vector associated with the first block as a motion vector predictor and in response to performing the motion vector refinement on the first motion vector for the first block, use a different motion vector than the first refined motion vector as the motion vector predictor associated with the first block.

Abstract: A co-located block of a video block to be decoded is determined. The co-located block is either (i) a forward reference block or (ii) a backward reference block. A reference motion vector is selected for the video block. When the co-located block is backward reference block and has a forward reference motion vector and a backward reference motion vector, the forward reference motion vector of the co-located block is selected. When the co-located block is forward reference block and has a forward reference motion vector and a backward reference motion vector, the backward reference motion vector of the co-located block is selected. When the co-located block has only one reference motion vector, the one reference motion vector of the co-located block is selected. When the co-located block has no reference motion vector, a zero-reference motion vector for the video block is selected.

Abstract: A reference frame decoding method includes obtaining a first reference frame, where the first reference frame is a first picture frame on which decoding reconstruction has been performed or a first interpolated picture frame obtained by pixel interpolation on the first picture frame, parsing a bitstream to obtain mapping parameters, determining to-be-determined coefficients of a preset mapping function according to the mapping parameters, obtaining, in the first reference frame according to the mapping function whose to-be-determined coefficients have been determined, a first pixel unit having a mapping relationship with a second pixel unit of a second reference frame, and assigning a pixel value of the first pixel unit to the second pixel unit.