Abstract: A video coder may determine a motion vector of a non-adjacent block of a current picture of the video data. The non-adjacent block is non-adjacent to a current block of the current picture. Furthermore, the video coder determines, based on the motion vector of the non-adjacent block, a motion vector predictor (MVP) for the current block. The video coder may determine a motion vector of the current block. The video coder may also determine a predictive block based on the motion vector of the current block.

Abstract: A three-dimensional data encoding method includes encoding information of a current node included in an N-ary tree structure of three-dimensional points included in three-dimensional data, where N is an integer greater than or equal to 2. In the encoding, reference to information of a first node included in neighboring nodes spatially neighboring the current node is permitted, and reference to information of a second node included in the neighboring nodes is prohibited, the first node having a same parent node as the current node, the second node having a different parent node from the parent node of the current node.

Abstract: Techniques are disclosed relating to selecting a number of candidates based on priority. In some embodiments, position determination circuitry receives an input vector that orders a set of potential candidates from a highest-priority position within the input vector to a lowest priority position. In some embodiments, it determines, starting from a first end of the input vector and based on non-overlapping groups of candidates, a particular position within the input vector at which a threshold number of available candidate are found. This may include to generate respective count values within the groups of candidates, identify a transition group in which the particular position is located based on accumulation of the respective count values, and identify the particular position within the transition group. Output circuitry may generate, based on the particular position, an output vector that indicates the threshold number of available candidates from the input vector.

Abstract: Video encoding or decoding includes performing affine motion compensation in an affine mode in which a prediction unit (“PU”) of the digital video coded in the affine mode uses inter prediction and a reference block bounding box size and determining whether the reference block bounding size exceeds a predefined threshold. In response to a determination that the reference block bounding size exceeds the predefined threshold, the affine motion compensation is performed using a first motion compensation operation. In response to a determination that the reference block bounding size does not exceed the predefined threshold, the affine motion compensation is performed using a second motion compensation operation that is different from the first motion compensation operation.

Abstract: According to some aspects of the disclosure, processing circuitry for point cloud decompression can decode prediction information of an image from a coded bitstream corresponding to a point cloud. The prediction information indicates that the image includes a first portion corresponding to patches in the point cloud, and a second portion corresponding to missed points by the patches from the point cloud. The processing circuitry can scan the second portion of the image according to a non-jumpy scan to obtain the missed points in a sequence, and reconstruct the point cloud based on reconstructed patches corresponding to the patches and reconstructed missed points based on the sequence of the missed points.

Abstract: A Frame Rate Up-Conversion (FRUC) derivation process, based on frame rate up-conversion techniques, is developed in the reference software JEM (Joint Exploration Model) by the Joint Video Exploration Team (JVET). In one embodiment, a modified FRUC derivation process improves the performances of the current FRUC tool is provided. For example, some candidates of a bi-predictive pair may be discarded initially, which would save signification processing time. The discarding decision may depend on various criteria such as, e.g., a ratio between matching costs of a bi-predictive pair from two reference picture lists, a difference between the matching costs of a bi-predictive pair normalized by their respective template areas.

Abstract: A method of decoding motion information according to an embodiment includes: obtaining information indicating a disparity distance for determining a prediction motion vector of a current block; scaling the disparity distance corresponding to the obtained information, based on a comparison result between a base pixel unit and a smallest pixel unit indicatable by a motion vector of the current block; determining a prediction motion vector candidate changed by the scaled disparity distance from a base motion vector of the current block from among one or more prediction motion vector candidates as the prediction motion vector of the current block; and determining the motion vector of the current block by using the prediction motion vector.

Abstract: An image block is coded using entropy-inspired directional filtering. During encoding, intensity differences are determined for at least some pixels of an image block based on neighboring pixels of respective ones of the at least some pixels. Angles are estimated for each of those pixels based on the intensity differences. A main filtering direction of the image block is then determined based on the estimated angles. The image block is filtered according to the main filtering direction to remove artifacts along oblique edges associated with the image block. The filtered image block is then encoded to an encoded image. During decoding, an angular map indicating angles estimated for pixels of an encoded image block is received and used to determine the main filtering direction of the image block. The image block can then be filtered according to the main filtering direction and then output for display or storage.

Abstract: An encoder includes: circuitry; and memory coupled to the circuitry. In operation, the circuitry: derives a base motion vector to be used in predicting a current block to be encoded; derives a first motion vector different from the base motion vector; derives a motion vector difference based on a difference between the base motion vector and the first motion vector; determines whether the motion vector difference is greater than a threshold; modifies the first motion vector when the motion vector difference is determined to be greater than the threshold, and does not modify the first motion vector when the motion vector difference is determined not to be greater than the threshold; and encodes the current block using the first motion vector modified or the first motion vector not modified.

Abstract: A video decoding method according to an embodiment of the present invention may include determining a type of a filter to be applied to a first-layer picture which a second-layer picture as a decoding target refers to; determining a filtering target of the first-layer picture to which the filter is applied; filtering the filtering target based on the type of the filter; and adding the filtered first-layer picture to a second-layer reference picture list. Accordingly, the video decoding method and an apparatus using the same may reduce a prediction error in an upper layer and enhance encoding efficiency.

Abstract: Systems, methods, and computer-readable storage media for maintaining palette predictors for palette coding are described. An example method can include determining a current palette coding block of a single tree coded slice of a picture is encoded according to a local dual tree; determining, after an update of a palette predictor associated with the current palette coding block, a first number of palette predictor entries for a first image component of the current palette coding block and a second number of palette predictor entries for a second image component of the current palette coding block; determining the first number of palette predictor entries is greater than the second number of palette predictor entries; and based on the first number being greater than the second number, modifying the updated palette predictor to include a same number of palette predictor entries for the first and second image component.

Abstract: An inter prediction method according to the present invention comprises: a step for deriving reference motion information related to a unit to be decoded in a current picture; and a step for performing motion compensation for the unit to be decoded, using the reference motion information that has been derived. According to the present invention, image encoding/decoding efficiency can be enhanced.

Abstract: According to an embodiment, an encoding device includes a deriving unit and an encoding unit. The deriving unit is configured to derive a first reference value based on fixed point precision representing roughness of a weighting factor that is used for multiplying a reference image. The encoding unit is configured to encode a first difference value that is a difference value between the weighting factor and the first reference value and the fixed point precision. The weighting factor is included in a first range of predetermined bit precision having the first reference value at approximate center. The first difference value is in the predetermined range.

Abstract: The present disclosure concerns a method and a device for encoding or decoding video data. It concerns more particularly the encoding according to a particular encoding mode using a decoder side motion vector derivation mode referenced as frame-rate up conversion mode or FRUC mode. It concerns encoding and decoding improvement which reduce the need for memory accesses when using an encoding mode where the motion information is predicted using a decoder side motion vector derivation method.

Abstract: A method for decoding a 360-degree image includes: receiving a bitstream obtained by encoding a 360-degree image; generating a prediction image by making reference to syntax information obtained from the received bitstream; combining the generated prediction image with a residual image obtained by dequantizing and inverse-transforming the bitstream to obtain a decoded image; and reconstructing the decoded image into a 360-degree image according to a projection format.

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 performs downscaling of an image frame prior to video encoding and a decoder performs upscaling of an image frame subsequent to video decoding.

Abstract: A video coding or decoding method includes using history-based motion vector prediction (HMVP) for conversion between multiple video blocks including a current block of video and a bitstream representation of the multiple video blocks such that for a uni-predicted block that for which a single reference picture is used for motion compensation, refraining from updating a look-up table for HMVP candidates for the uni-predicted block. The video coding or decoding method further includes performing the conversion using look-up tables for the multiple video blocks.

Abstract: A motion vector prediction method and device, includes determining a motion vector type of the motion vector of the current block based on a reference frame type of the reference frame, obtaining a motion vector type of a first motion vector of at least one spatially adjacent prediction block of the current block when the at least one spatially adjacent prediction block is an inter-frame prediction block, and when the obtained motion vector type of the first motion vector is different from all motion vector types of motion vectors of the current block, determining a second motion vector of a spatially adjacent pixel block of the current block based on decoding information of the spatially adjacent pixel block, and using the second motion vector or a scaling value of the second motion vector as a candidate motion vector predictor of the current block.

Abstract: In various embodiments, a subsequence-based encoding application generates a convex hull of subsequence encode points based on multiple encoding points and a first subsequence included in a set of subsequences that are associated with a media title. The subsequence-based encoding application then generates a first encode list that includes multiple subsequence encode points based on the first convex hull. Notably, each subsequence encode point included in the first encode list is associated with a different subsequence. The subsequence-based encoding application selects a first subsequence encode point included in the first encode list based on a first variability constraint that is associated with a media metric. The subsequence-based encoding application then replaces the first subsequence encode point included in the first encode list with a second subsequence encode point to generate a second encode list.

Abstract: Provided are embodiments including a computer-implemented method for performing recognition. The computer-implemented method includes receiving video data, and performing, at a pre-attention prediction module, a pre-attention prediction for the video data to generate first prediction priors. The computer-implemented method also includes receiving, at a dual attention module, data including the video data and data from the pre-attention prediction to generate attention maps, wherein the attention maps indicate a region of interest of a frame of the video data, wherein the dual attention module generates enhanced feature representations, and performing, at a post-attention prediction module, a post-attention prediction from data from the dual attention module based at least in part on the enhanced feature representation. Also provided are embodiments for a system and a computer program produce for performing recognition.

Abstract: A decoding method includes obtaining a rectangular region to be decoded in a picture, setting a first template region in accordance with a position of the rectangular region, setting a second template region corresponding to the first template region in a reference picture, setting third template regions each of which is obtained by moving the second template region using a corresponding vector in the reference picture, calculating image correlation values each of which is obtained between a corresponding one of the third template regions and the first template region, determining a motion vector of the rectangular region, wherein the setting a first template region includes setting a region adjacent to a predetermined block including the rectangular region as the first template region when a size of the rectangular region is a predetermined threshold size or smaller, or when a picture including the rectangular region corresponds to a non-reference picture.

Abstract: A video encoding and decoding method, apparatus, a computer device, and a storage medium. The method includes obtaining a current frame to be encoded; determining a resolution determining mechanism among a plurality of resolution determining mechanisms to be performed on a reference frame based on a resolution relationship between the current frame and a reference frame corresponding to the current frame; generating the reference frame corresponding to the current frame according to the resolution determining mechanism; and encoding the current frame according to the reference frame to obtain encoded data corresponding to the current frame, the encoded data including the resolution relationship.

Abstract: A method includes receiving a current block to be coded and splitting the current block into a plurality of sub-partitions. A first set of reference pixels is determined. The method processes a first sub-partition in the plurality of sub-partitions using the first set of reference pixels and a second sub-partition in the plurality of sub-partitions using the first set of reference pixels in parallel. Then, the method processes a third sub-partition in the plurality of sub-partitions based on a second set of reference pixels determined from the processing of the first sub-partition and processing a fourth sub-partition in the plurality of sub-partitions based on a third set of reference pixels determined from the processing of the second sub-partition.

Abstract: A method for video processing is provided to comprise: determining a motion vector precision of one or more motion vectors related to a current video block of a video; selecting, based on the motion vector precision, a motion vector range; and performing, based on the motion vector range, a conversion between the current video block and a bitstream representation of the video.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. An apparatus for video decoding includes processing circuitry that decodes prediction information for a current block in a current coded picture. The prediction information indicates a motion vector predictor index (MVP_idx) for selecting a motion vector predictor in a motion vector predictor list. The processing circuitry determines whether the MVP_idx is smaller than a threshold. When the MVP_idx is determined to be smaller than the threshold, the processing circuitry decodes a motion vector difference (MVD) corresponding to the motion vector predictor and reconstructs the current block based on the motion vector predictor and the MVD. When the MVP_idx is determined to be equal to or larger than the threshold, the processing circuitry reconstructs the current block based on the motion vector predictor without the MVD which is not signaled in the coded video sequence.

Abstract: A video image processing method includes dividing a coding tree unit into one or more coding units using a quadtree plus binary tree division method, obtaining a motion vector candidate list of one of the one or more coding units, determining a base motion vector according to motion vectors in the motion vector candidate list, in response to the base motion vector pointing to a short-term reference image, scaling the base motion vector using a scaling factor not equal to 1, in response to the base motion vector pointing to a long-term reference image, scaling the base motion vector using a scaling factor set to 1, and performing prediction for the one of the one or more coding units according to the base motion vector after being scaled.

Abstract: An apparatus for video decoding includes receiving circuitry and processing circuitry. In some embodiments, 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 that signals a value associated with a motion vector difference in the coded video bitstream. The processing circuitry determines a precision for the motion vector difference based on a size of the current block, and converts the signaled value in the coded video bitstream to the motion vector difference based on the determined precision. Then, the processing circuitry determines a motion vector based on a prediction of the motion vector and the motion vector difference, and reconstructs at least a sample of the current block according to the motion vector.

Abstract: A video data stream is rendered reducible in a manner so that the reduction leads to a restriction of pictures of the reduced video data stream to merely a predetermined subarea of the pictures of the original video data stream and in a manner so that transcoding, such as re-quantization, may be avoided and a conformance of the reduced video data stream relative to the codec underlying the original video data stream be maintained. This is achieved by providing the video data stream with information including an indication of the predetermined subarea and replacement indices for redirecting the indices included by the payload portion so as to refer to, and/or replacement parameters for adjusting the first set of coding parameter settings so as to result in, a second set of coding parameter settings.

Abstract: In one example, a method of coding video data includes responsive to determining to predict a current block of a current picture of video data using intra block copy (IBC), generating a motion vector (MV) candidate list for the current block, wherein generating the MV candidate list comprises: determining one or more history-based motion vector prediction (HMVP) candidates; and including, as a last candidate in the MV candidate list, an HMVP candidate of the one or more HMVP candidates; selecting, from the MV candidate list, a particular MV candidate that identifies a predictor block in the current picture; and reconstructing pixels of the current block based on pixels of the predictor block.

Abstract: A system may include an electronic display panel having multiple pixels for depicting image data and processing circuitry that may receive a first error value representative of a first difference between a first electrical signal measured at a first pixel of the multiple pixels and an expected electrical signal for the first pixel. The first electrical signal may be based on a test signal transmitted to the first pixel and the expected electrical signal may correspond to an expected response of the first pixel based on the test signal. The processing circuitry may filter the first error value to generate a first compensated error value and may filter the first error value based on the first compensated error value to generate a second compensated error value, where the second compensated error value may filter one or more effects of spatial crosstalk between one or more pixels near the first pixel.

Abstract: A method of processing a video signal is disclosed. The present invention includes obtaining a current macroblock type, obtaining skip or direct mode indication information on a partition of the current macroblock according to the current macroblock type, deriving a motion vector of the partition according to the skip or direct mode indication information, and predicting a pixel value of the partition using the motion vector. Accordingly, the present invention obtains a pixel value of a reference block close to an original video using a motion vector, thereby enhancing a reconstruction ratio of the macroblock. As a macroblock uses skip or direct prediction indication information, it is unnecessary to separately code skip mode indication information and direct mode indication information on the macroblock, whereby an information size to be coded can be reduced.

Abstract: The subject technology receives image data and depth data. The subject technology selects an augmented reality content generator corresponding to a three-dimensional (3D) effect. The subject technology applies the 3D effect to the image data and the depth data based at least in part on the selected augmented reality content generator. The subject technology generates, using a processor, a message including information related to the applied 3D effect, the image data, and the depth data.

Abstract: The present invention relates to a video encoding method, a video decoding method, and a device using the same, and the video encoding method according to the present invention comprises the steps of: specifying a tile and a slice by partitioning an inputted picture; performing encoding on the basis of the tile and the slice; and transmitting the encoded video information, wherein the picture is partitioned into one or more tiles and one or more slices, and the restrictions for parallel processing can be applied to the tiles and the slices.

Abstract: A vehicular vision system includes a control disposed at a vehicle. A camera is disposed at an in-cabin side of the vehicle windshield and views forward of the vehicle. During a driving maneuver of the vehicle, the vehicular vision system, responsive at least in part to an output of a radar sensor, detects an object that is located within the radar sensor's field of sensing and outside of the camera's field of view and determines movement of the object relative to the vehicle. During the driving maneuver of the vehicle, information pertaining to movement of the detected object toward an area within the field of view of the camera is provided to the control. During the driving maneuver, and responsive to the provided information, and with the detected object present within the camera's field of view, the vehicular vision system determines that the detected object is an object of interest.

Abstract: Aspects of the disclosure provide a method and an apparatus for video decoding. Processing circuitry of the apparatus decodes prediction information of a current block from a coded video bitstream. The prediction information indicates an inter prediction mode. The processing circuitry calculates at least one hash value based on motion information of a previously decoded block and determines whether the motion information is different from one or more motion information candidates in a candidate list for the current block based on the at least one hash value of the previously decoded block and at least one hash value of each of the one or more motion information candidates. The processing circuitry adds the motion information to the candidate list when the motion information is different from the one or more motion information candidates and reconstructs at least one sample of the current block based on the candidate list.

Abstract: A method is described of forming a bitstream by an encoder apparatus comprising: a processor of the encoder apparatus receiving a projected video frame including one or more pixel regions, the one or more pixel regions representing pixels of spherical video data projected onto one or more 2D projection surfaces of a projection model, the projection model being adapted to project spherical video data onto a rectangular 2D surface of a video frame; the processor generating a plurality of different candidate video frames on the basis of the received projected video frame, each candidate video frame being formed by applying at least one operation to one or more groups of pixels in one or more pixel regions of the projected video frame, wherein said at least operation includes a shift, mirror and/or rotation operation; and, wherein said operation is different for each of said plurality of different candidate video frames; the processor applying a rate distortion analysis to each of the candidate video frames to de

Abstract: Example embodiments herein provide a method for coding a segment of an inter frame. The method includes partitioning, by a partitioning unit, a current frame into a plurality of segments. Further, the method includes coding, by a coding unit, a current spatial block at a boundary of a segment included among the plurality of segments by deriving at least one new temporal motion information predictor candidate from a reference frame. Further, the method includes cabac context initialization at the start of each non-first segment from the plurality of segments by deriving temporal stored cabac context from the reference frame.

Abstract: The present disclosure relates to a method and apparatus for improving the encoding efficiency by adaptively changing the resolution of the motion vector in the inter prediction encoding and inter prediction decoding of a video. The apparatus includes: a predicted motion vector calculator for calculating a predicted motion vector of a current block to be encoded using motion vectors of one or more surrounding blocks; and a skip mode encoder for encoding a result of performing a prediction of the current block and information indicating that the current block is a skip block when the predicted motion vector satisfies a skip condition, wherein at least one motion vector among the motion vectors of the surrounding blocks and the motion vector of the current block has a resolution different from resolutions of the other motion vectors.

Abstract: Described are techniques in video coding and/or decoding that allow for selectively breaking prediction and/or in loop filtering across segment boundaries between different segments of a video picture. A high layer syntax element, such as a parameter set or a slice header, may contain one or more indications signalling to an encoder and/or decoder whether an associated prediction or loop filtering tool may be applied across the segment boundary. In response to such one or more indications, the encoder and/or decoder may then control the prediction or loop filtering tool accordingly.

Abstract: A picture prediction method includes: determining two pixel samples in a current picture block, and determining a candidate motion information unit set corresponding to each of the two pixel samples; determining a merged motion information unit set i including two motion information units; and predicting a pixel value of the current picture block by using an atone motion model and the merged motion information unit set i.

Abstract: A method for decoding a video according to the present invention may comprise: deriving a spatial merge candidate for a current block from at least one of a first spatial neighboring block adjacent to the current block or a second spatial neighboring block adjacent to the first spatial neighboring block, generating a merge candidate list including the spatial merge candidate, and performing a motion compensation for the current block by using the merge candidate list.

Abstract: A combined prediction mode for encoding or decoding a pixel block of a video picture is provided. When it is determined that the combined prediction mode is used, a video codec generates an intra predictor for the current block based on a selected intra-prediction mode and a merge-indexed predictor for the current block based on a selected merge candidate from a merge candidates list. The video codec then generates a final predictor for the current block based on the intra predictor and the merge-indexed predictor. The final predictor is then used to encode or decode the current block.

Abstract: A method and an apparatus for video decoding are disclosed. The apparatus decodes prediction information of a current block from a coded video bitstream. The prediction information indicates an intra block copy mode. The current block is one of a plurality of coding blocks in a current region of a current coding tree block (CTB) in a current picture. The apparatus determines whether the current block is to be reconstructed first in the current region. When the current block is to be reconstructed first in the current region, the apparatus determines a block vector for the current block where a reference block indicated by the block vector is in a search range in the current picture that excludes a collocated region in a previously reconstructed CTB. A position of the collocated region in the previously reconstructed CTB has a same relative position as the current region in the current CTB.

Abstract: An example device for coding video data is configured to determine that a block of the video data includes a plurality of sub-blocks, each of the sub-blocks having respective motion information referring to respective reference blocks in a reference picture in a memory, determine a single reference block of the reference picture, the single reference block including each of the respective reference blocks, wherein determining the single reference block comprises: determine four corner sub-blocks of the block included in the plurality of sub-blocks; and determine the single reference block according to the respective motion information for the four corner sub-blocks such that corners of the single reference block correspond to corners of the respective reference blocks of the four corner sub-blocks, retrieve data of the single reference block from the reference picture, and predict the sub-blocks from the respective reference blocks using the data of the single reference block.

Abstract: A method of decoding motion information according to an embodiment includes: determining a base motion vector of a current block; determining a primary differential motion vector for the current block based on information obtained from a bitstream from among one or more primary differential motion vector candidates classified according to a disparity distance and a disparity direction; and determining a motion vector of the current block by applying the primary differential motion vector to the base motion vector.

Abstract: A picture prediction method and a related apparatus are disclosed. A picture prediction method includes: determining K1 pixel samples in a picture block x, and determining a candidate motion information unit set corresponding to each pixel sample in the K1 pixel samples, where the candidate motion information unit set corresponding to each pixel sample includes at least one candidate motion information unit; determining a merged motion information unit set i including K1 motion information units, where each motion information unit in the merged motion information unit set i is selected from at least a part of motion information units in candidate motion information unit sets corresponding to different pixel samples in the K1 pixel samples; and predicting a pixel value of the picture block x by using a non-translational motion model and the merged motion information unit set i.

Abstract: A video coder may determine a partitioning of a current picture of the video data into a plurality of partition blocks. The video coder may determine a plurality of processing areas in a unit in the current picture having sizes, where an average size of all of the plurality of processing areas in the unit is greater than or equal to a parameter N, and where determining the plurality of processing areas in the unit includes defining a processing area of the plurality of processing areas that has a size that fits two or more adjacent partition blocks of the plurality of adjacent blocks. The video coder may independently code coding units (CUs) within the processing area having the merged two or more adjacent partition blocks.

Abstract: A method of encoding and a device for encoding a data stream representative of an omnidirectional video and, correlatively, a method for decoding and a device for decoding a data stream representative of an omnidirectional video. The data stream is representative of an omnidirectional video and includes encoded data of at least one base layer representative of a 2D or 3D video representative of a view of a scene captured by the omnidirectional video, and encoded data of at least one enhancement layer representative of the omnidirectional video. The least one enhancement layer is encoded by prediction relative to the at least one base layer.

Abstract: The present invention relates to an object region detection method, an object region detection apparatus, and a non-transitory computer-readable medium thereof, and more particularly, to an object region detection method, an object region detection apparatus, and a non-transitory computer-readable medium thereof, capable of further accelerating analysis of object recognition and tracking by preliminarily detecting an object region based on a parameter value obtained from an image decoding process and referring to the detected object region for image analysis.

Abstract: A method of processing point cloud data at a decoder can include receiving three dimensional (3D) coordinates of a set of points of a point cloud including first points and a current point. Each of the first points can be associated with a reconstructed attribute value. A group of neighboring points of the current point can be determined from the first points. An indicator is received. The indicator indicates whether reconstruction of the current point in a prediction step in a lifting scheme is based on a weighted average prediction of the reconstructed attribute values of the plurality of neighboring points. The current point is reconstructed based on the received indicator.