Abstract: When a coding mode selected by an encoding controlling part 1 is an intra prediction mode, an intra prediction part 4 carries out an intra-frame prediction process using pixels adjacent to a partition Pin which is generated through a division by a block dividing part 2 or pixels adjacent to a higher layer partition Pin?1 to which the partition Pin belongs to generate a prediction image (Pin).

Abstract: The present invention is made to enable switching between lossless coding which prioritizes compatibility with a lossy coding process and lossless coding which prioritizes compression performance. An image coding apparatus of the present invention includes the following configuration. The image coding apparatus which encodes an image on a block-by-block basis includes a first coding unit and a second coding unit. The first coding unit performs irreversible compression coding on a received first block. The second coding unit performs reversible compression coding on a received second block. The second coding unit encodes the second block by using either of a first intra prediction mode for performing intra prediction on a block-by-block basis and a second intra prediction mode for performing intra prediction on a pixel-by-pixel basis.

Abstract: The object of the present invention is to provide a technique capable of effectively compressing point cloud data output from the ranging sensor. A data compression apparatus of the present invention includes a data acquisition unit (121) which acquires point cloud data including a plurality of sets each including a direction and a distance from a ranging sensor (11), a data conversion unit (122) which converts directions and distances in the sets into color signals, an image generation unit (123) which generates a bitmap Image by mapping the color signals into a two-dimensional data structure in accordance with the directions, and an image compression unit (124) which applies a predetermined image compression technique to the bitmap image.

Abstract: Virtual boundary processing in adaptive loop filtering (ALF) requires that padded values be substituted for unavailable pixel rows outside the virtual boundaries. Methods and apparatus are provided for virtual boundary processing in ALF that allow the use of more actual pixel values for padding than in the prior art.

Abstract: Aspects of the present disclosure relate to identifying friction points in customer data. In some embodiments, identifying friction points can include receiving a set of input sequence data and predicted class labels for the set of input sequence data; selecting input sequences, from the set of input sequence data, that have class labels matching a ground truth class label; reducing the selected sequences to anchor points; and grouping the reduced selected sequences into critical data set signatures using discriminatory subsequence mining.

Abstract: A video processing apparatus implemented in a chip includes an on-chip prediction buffer and a processing circuit. The on-chip prediction buffer is shared by a plurality of coding tools for prediction, and is used to store reference data. The processing circuit supports the coding tools for prediction, reads a plurality of first reference data from the on-chip prediction buffer as input data of a first coding tool that is included in the coding tools and enabled by the processing circuit, and writes output data of the first coding tool enabled by the processing circuit into the on-chip prediction buffer as a plurality of second reference data.

Abstract: Systems and methods herein provide for data deduplication in memory. In one embodiment, an Input/Output (I/O) module is operable to process a write I/O request to the memory, and to extract data of the write I/O request. A data deduplication module is operable to access a table to identify a first portion of the data of the write I/O request that is stored at a first address of the memory, to assign a pointer to the first portion of the data in the table, to identify a second portion of the data of the write I/O request that is not stored in memory, and to direct the second portion of the data of the write I/O request to be written to a second address of the memory.

Abstract: Systems and methods for image tagging are described. In some embodiments, images with problematic tags are identified after applying an auto-tagger. The images with problematic tags are then sent to an object detection network. In some cases, the object detection network is trained using a training set selected to improve detection of objects associated with the problematic tags. The output of the object detection network can be merged with the output of the auto-tagger to provide a combined image tagging output. In some cases, the output of the object detection network also includes a bounding box, which can be used to crop the image around a relevant object so that the auto-tagger can be reapplied to a portion of the image.

Abstract: A method and apparatus for media decoding by a decoder include decoding a first indication indicative of a first conformance point of a coded video sequence. A second indication indicative of a second conformance point of the coded video sequence is decoded. It is determined whether the coded video sequence is decodable by the decoder based on at least one of the first indication and the second indication. The coded video sequence is selectively decoded based on determining whether the decoded video sequence is decodable by the decoder.

Abstract: A coding tool is provided to improve the compression performance of inter prediction and is used at the encoder/decoder side to adjust the correction of a motion vector based on a high level syntax. In addition, a method is provided for simply performing an integer sample search step of searching for an integer offset and a fractional sample refinement step of searching for a sub-pixel offset in relation to motion vector refinement among coding tools.

Abstract: An encoding, a decoding method, a system for encoding and decoding, an encoder, and a decoder are provided. The encoding method includes the following. In a palette mode, if colors of pixels of a coding unit block are all represented by one or more major colors of the coding unit block, a flag is set as a first state value, and if the color of at least one pixel of the coding unit block is not represented by the one or more major colors of the coding unit block, the flag is set as a second state value. The encoding method further includes establishing a palette table corresponding to the coding unit block according to a state value of the flag and the one or more major colors.

Abstract: Methods of encoding and decoding for video data are described for encoding or decoding multi-level significance maps. Distinct context sets may be used for encoding the significant-coefficient flags in different regions of the transform unit. In a fixed case, the regions are defined by coefficient group borders. In one example, the upper-left coefficient group is a first region and the other coefficient groups are a second region. In a dynamic case, the regions are defined by coefficient group borders, but the encoder and decoder dynamically determine in which region each coefficient group belongs. Coefficient groups may be assigned to one region or another based on, for example, whether their respective significant-coefficient-group flags were inferred or not.

Abstract: A load balancing method for video decoding. The load balancing includes first determining which hardware devices are suitable for the new decoding process, and determining the current load of each of the suitable hardware devices. From the suitable devices potential devices are selected having a current load less than a threshold and overloaded devices are selected having a load greater than or equal to the threshold. If there are no suitable devices, then the decoding process is implemented by software decoding. If the list of potential hardware devices includes only one potential hardware device, then the decoding process is implemented on the hardware device. If the list of potential hardware devices includes more than one potential hardware device, then it is determined how many decoding processes are currently running on each potential hardware device, and the new decoding process is implemented on the potential hardware device having the fewest processes.

Abstract: A system includes a non-transitory computer readable medium configured to store instructions thereon; and a processor connected to the non-transitory computer readable medium. The processor is configured to execute the instructions for generating a mask based on received data from a sensor, wherein the mask includes a plurality of importance values, and each region of the received data is designated a corresponding importance value of the plurality of importance values. The processor is configured to execute the instructions for encoding the received data based on the mask; and transmitting the encoded data to a decoder for defining reconstructed data. The processor is configured to execute the instructions for computing a loss based on the reconstructed data, the received data and the mask. The processor is configured to execute the instructions for providing training to an encoder for encoding the received data based on the computed loss.

Abstract: A coding tool is provided to improve the compression performance of inter prediction and is used at the encoder/decoder side to adjust the correction of a motion vector based on a high level syntax. In addition, a method is provided for simply performing an integer sample search step of searching for an integer offset and a fractional sample refinement step of searching for a sub-pixel offset in relation to motion vector refinement among coding tools.

Abstract: An image decoding method of decoding, on a block-by-block basis, image data included in a coded stream includes: deriving candidates for an intra prediction mode to be used for intra prediction for a decoding target block, the number of the candidates constantly being a plural number; obtaining, from the coded stream, an index for identifying one of the derived candidates for the intra prediction mode; and determining, based on the obtained index, one of the derived candidates for the intra prediction mode as the intra prediction mode to be used for intra prediction for the decoding target block.

Abstract: Methods and apparatus for in-loop processing of reconstructed video are disclosed. According to one method, a virtual boundary is determined for to-be-processed pixels in the current picture, where the virtual boundary is aligned with block boundaries and at least one to-be-processed pixel on a first side of the virtual boundary requires one or more second pixels on a second side of the virtual boundary. According to the method, the in-loop processing is modified if a target to-be-processed pixel requires at least one second pixel from the second side of the virtual boundary and the modified in-loop processing eliminates the need for any second pixel on the second side of the virtual boundary. According to another method, the operations of block classification are changed when part of the required pixels in one 10×10 window used in classification are at the other side of virtual boundaries.

Abstract: Certain aspects of the present disclosure are directed to methods and apparatus for compressing video content using deep generative models. One example method generally includes receiving video content for compression. The received video content is generally encoded into a latent code space through an encoder, which may be implemented by a first artificial neural network. A compressed version of the encoded video content is generally generated through a trained probabilistic model, which may be implemented by a second artificial neural network, and output for transmission.

Abstract: An encoding device configured to encode a flag, that indicates whether tile information for a picture having a tile group is present in a parameter set of a video bitstream or in a slice header of the video bitstream, into the video bitstream, encode the tile information in the parameter set when the flag indicates the tile information for the picture is encoded in the parameter set, and encode the tile information in the slice header when the flag indicates the tile information for the picture is encoded in the slice header.

Abstract: Systems and methods in accordance with embodiments of the invention are configured to render images using light field image files containing an image synthesized from light field image data and metadata describing the image that includes a depth map. One embodiment of the invention includes a processor and memory containing a rendering application and a light field image file including an encoded image, a set of low resolution images, and metadata describing the encoded image, where the metadata comprises a depth map that specifies depths from the reference viewpoint for pixels in the encoded image. In addition, the rendering application configures the processor to: locate the encoded image within the light field image file; decode the encoded image; locate the metadata within the light field image file; and post process the decoded image by modifying the pixels based on the depths indicated within the depth map and the set of low resolution images to create a rendered image.

Abstract: An image decoder performs a first partitioning including using a first partition mode, without parsing first splitting information indicative of the first partition mode, to split a first block into a plurality of second blocks in response to that the first block is located adjacent to an edge of a picture and that the dimensions of the first block satisfy a first condition; and performs a second partitioning on the second block by parsing second splitting information indicative of a second partition mode, wherein the second partition mode allows at least one of a quad tree splitting and a binary splitting, and using the second partition mode to split the second block into a plurality of coding units (CUs), wherein the second partition mode prohibits the quad tree splitting of the second block in response to that the second block is located adjacent to the edge of the picture.

Abstract: An image decoding method according to the present document comprises the steps of: deriving transform coefficients through inverse quantization on the basis of quantized transform coefficients for a target block; deriving modified transform coefficients on the basis of an inverse reduced secondary transform (RST) for the transform coefficients; and generating, on the basis of an inverse primary transform for the modified transform coefficients, a restoration picture based on residual samples for the target block, wherein the modified transform coefficients derived according to the inverse RST are two-dimensionally arranged according to the order of a row priority direction or a column priority direction according to an intra prediction mode to be applied to the target block.

Abstract: Aspects of the disclosure include methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. An apparatus includes processing circuitry that decodes prediction information of a current block in a current picture that is a part of a coded video bitstream. The prediction information indicates a non-directional intra prediction mode for the current block. The processing circuitry partitions the current block into a plurality of partitions. The plurality of partitions includes at least one L-shaped partition. The processing circuitry reconstructs one of the plurality of partitions based on at least one of (i) neighboring reconstructed samples of the one of the plurality of partitions or (ii) neighboring reconstructed samples of the current block.

Abstract: The present invention relates to an image encoding and decoding technique, and more particularly, to an image encoder and decoder using unidirectional prediction. The image encoder includes a dividing unit to divide a macro block into a plurality of sub-blocks, a unidirectional application determining unit to determine whether an identical prediction mode is applied to each of the plurality of sub-blocks, and a prediction mode determining unit to determine a prediction mode with respect to each of the plurality of sub-blocks based on a determined result of the unidirectional application determining unit.

Abstract: A coding tool is provided to improve the compression performance of inter prediction and is used at the encoder/decoder side to adjust the correction of a motion vector based on a high level syntax. In addition, a method is provided for simply performing an integer sample search step of searching for an integer offset and a fractional sample refinement step of searching for a sub-pixel offset in relation to motion vector refinement among coding tools.

Abstract: A method for encoding a picture of a video sequence in a bit stream that reduces slice header parsing overhead is provided. The method includes determining weighting factors that may be used for weighted prediction in encoding at least one slice of the picture, wherein a total number of the weighting factors is constrained to not exceed a predetermined threshold number of weighting factors, wherein the threshold number is less than a maximum possible number of weighting factors, and signaling weighted prediction parameters including the weighting factors in a slice header in the bit stream.

Abstract: Methods and devices for intra-prediction of a current block in video encoding or decoding are provided. A method includes: performing intra-prediction processing of the current block according to a directional intra-prediction mode, including applying reference sample filtering or subpixel interpolation filtering to reference samples in one or more reference blocks, wherein the directional intra-prediction mode is classified into one of the following groups: (A) vertical or horizontal modes, (B) directional modes including diagonal modes that represent angles which are multiples of 45 degrees, (C) remaining directional modes; if the directional intra-prediction mode is classified as belonging to group B, a reference sample filter is applied to the reference samples; if the directional intra-prediction mode is classified as belonging to group C, an intra reference sample interpolation filter is applied to the reference samples.

Abstract: A dependency indication is signaled within the beginning of a packet, that is, within the adjacent of a slice header to be parsed or a parameter set. This is achieved, for example, by including the dependency indication at the beginning of the slice header, preferably after a syntax element identifying the parameter set and before the slice address, by including the dependency indication before the slice address, by providing the dependency indication to a NALU header using a separate message, or by using a special NALU type for NALUs carrying dependent slices.

Abstract: A method and apparatus, a communication device and a storage medium for information processing are provided. The method includes determining application information of a target application and terminal information of a terminal. The target application is an application requiring use of a network slice for data transmission and the terminal information is able to reflect a terminal capability of the terminal. The method further includes sending request information to a server according to the application information and the terminal information. The method also includes receiving slice information returned by the server based on the request information. A network slice indicated by the slice information is matched with the target application and the terminal capability. The method further includes transmitting data of the target application based on the network slice indicated by the slice information.

Abstract: Memory required during decoding is reduced. A video image decoding device (1) is equipped with main direction deriving means (1453A) that references a prediction mode definition DEFPM(1), and from a prediction mode number, derives a main direction of a prediction direction corresponding to a prediction mode, and a gradient deriver (1453B) that references a gradient definition table DEFANG(1), and derives a gradient of the prediction direction.

Abstract: Systems, methods, and instrumentalities are provided to implement video coding system (VCS). The VCS may be configured to receive a video signal, which may include one or more layers (e.g., a base layer (BL) and/or one or more enhancement layers (ELs)). The VCS may be configured to process a BL picture into an inter-layer reference (ILR) picture, e.g., using picture level inter-layer prediction process. The VCS may be configured to select one or both of the processed ILR picture or an enhancement layer (EL) reference picture. The selected reference picture(s) may comprise one of the EL reference picture, or the ILR picture. The VCS may be configured to predict a current EL picture using one or more of the selected ILR picture or the EL reference picture. The VCS may be configured to store the processed ILR picture in an EL decoded picture buffer (DPB).

Abstract: A method includes receiving sensor data from a plurality of robot sensors on a robot. The method includes generating a depth map that includes a plurality of pixel depths. The method includes determining, for each respective pixel depth, based on the at least one robot sensor associated with the respective pixel depth, a pixelwise confidence level indicative of a likelihood that the respective pixel depth accurately represents a distance between the robot and a feature of the environment. The method includes generating a pixelwise filterable depth map for a control system of the robot. The pixelwise filterable depth map is filterable to produce a robot operation specific depth map. The robot operation specific depth map is determined based on a comparison of each respective pixelwise confidence level with a confidence threshold corresponding to at least one operation of the robot controlled by the control system of the robot.

Abstract: A method and system for reducing the number of colors per pixel present in an image to increase the ability to detect objects or anomalies in the image. A final number of colors per pixel to reduce the image to is determined, wherein the final number of colors is a number of colors less than the number of colors per pixel in the original image. A corresponding threshold value for each of the final number of colors is identified, such that the corresponding threshold values optimize an arithmetic combination of separation score functions applied to the plurality of pixels and the threshold values. The image is reduced to the final number of colors per pixel, by creating an output image where a value of each output pixel is equal to the number of threshold values that are less than the value of the corresponding input pixel.

Abstract: Dictionary-based compression is performed to compress data units using a similar data unit as the base unit (i.e., dictionary) for each candidate data unit. Similarity may be determined between data units by applying a locality-sensitive hashing scheme to each candidate data unit to produce a hash value, and by determining whether there is a matching value in a hash index of hash values for existing data units on the system. If there is a matching hash value, the candidate data unit may be compressed using the data unit corresponding to the matching hash value as the dictionary. Only a representative portion of the data unit may be hashed to produce the hash value, the portion comprised of chunks of the data unit, where each chunk is a continuous, uninterrupted section of data. The chunks themselves may not be (in some embodiments likely are not) contiguous to one another.

Abstract: Measures are provided to encode a signal. An input frame is received and down-sampled to obtain a down-sampled frame. The down-sampled frame is passed to an encoding module which encodes the down-sampled frame to generate an encoded frame. A decoded frame is obtained from a decoding module which generates the decoded frame by decoding the encoded frame. A set of residual data is generated by taking a difference between the decoded frame and the down-sampled frame and is encoded to generate a set of encoded residual data. The encoding comprises transforming the set of residual data into a transformed set of residual data. The set of encoded residual data is output to a decoder to enable the decoder to reconstruct the input frame. Measures are also provided to decode a signal.

Abstract: A three-dimensional data encoding method includes: extracting, from first three-dimensional data, second three-dimensional data having an amount of a feature greater than or equal to a threshold; and encoding the second three-dimensional data to generate first encoded three-dimensional data. For example, the three-dimensional data encoding method may further include encoding the first three-dimensional data to generate the second encoded three-dimensional data.

Abstract: The application provides a processing method and device. Weights and input neurons are quantized respectively, and a weight dictionary, a weight codebook, a neuron dictionary, and a neuron codebook are determined. A computational codebook is determined according to the weight codebook and the neuron codebook. Meanwhile, according to the application, the computational codebook is determined according to two types of quantized data, and the two types of quantized data are combined, which facilitates data processing.

Abstract: A method, computer program, and computer system is provided for partitioning encoded video data. Data corresponding to a video frame is received, and the video frame data may be divided the video frame data into one or more subunits. These subunits may each have unique address values and be arranged in increasing order based on the unique address values. A left boundary and a top boundary associated with each of the subunits may include one or more of a picture boundary or a boundary of previously decoded subunit.

Abstract: A method and apparatus of video coding operate by receiving input data associated with a current data unit in a current picture, wherein the current data unit includes a luma component and a chroma component and the current data unit includes a luma data unit and a chroma data unit. The operation proceeds by splitting the luma data unit and the Chroma data unit using one shared tree until the luma data unit and the chroma data unit reach a stop node, encoding or decoding the stop node as a leaf CU (coding unit) if the stop node is greater than M×N for the luma component, M and N are positive integers, and signalling or parsing a prediction mode for the stop node if the stop node is smaller than or equal to M×N for the luma component.

Abstract: To mitigate some problems of the pixel color mapping being used in HDR video decoding of the type of SLHDR, a high dynamic range video encoding circuit (300) is taught, configured to encode a high dynamic range image (IM_HDR) of a first maximum pixel luminance (PB_C1), together with a second image (Im_LWRDR) of lower dynamic range and corresponding lower second maximum pixel luminance (PB_C2), the second image being functionally encoded as a luma mapping function (400) for decoders to apply to pixel lumas (Y_PQ) of the high dynamic range image to obtain corresponding pixel lumas (PO) of the second image, the encoder comprising a data formatter (304) configured to output to a video communication medium (399) the high dynamic range image and metadata (MET) encoding the luma mapping function (400), the functional encoding of the second image being based also on a color lookup table (CL(Y_PQ)) which encodes a multiplier constant (B) for all possible values of the pixel lumas of the high dynamic range image, an

Abstract: The present disclosure provides an image encoder. The image encoder is configured to encode an original image and reduce compression loss. The image encoder comprises an image signal processor and a compressor. The image signal processor is configured to receive a first frame image and a second frame image and generates a compressed image of the second frame image using a boundary pixel image of the first frame image. The image signal processor may include memory configured to store first reference pixel data which is the first frame image. The compressor is configured to receive the first reference pixel data from the memory and generate a bitstream obtained by encoding the second frame image based on a difference value between the first reference pixel data and the second frame image. The image signal processor generates a compressed image of the second frame image using the bitstream generated by the compressor.

Abstract: Methods, systems and device for hash-based motion estimation in video coding are described. An exemplary method of video processing includes determining, for a conversion between a current block of a video and a bitstream representation of the video, motion information associated with the current block using a hash-based motion search, a size of the current block being M×N, M and N being positive integers and M being not equal to N, applying, based on the motion information and a video picture comprising the current block, a prediction for the current block, and performing, based on the prediction, the conversion.

Abstract: Systems, apparatuses and methods may a performance-enhanced computing system comprising a sensor for measuring luminance values corresponding to light focused onto the sensor at a plurality of pixel locations, a memory including a set of instructions, and a processor. The processor executes a set of instructions causing the system to generate a multi-segment tone mapping curve, generate a set of tone mapping values corresponding to the multi-segment tone mapping curve for equally spaced input values between zero and one for storage into a look up table, and process the luminance values using the look up table to apply the tone mapping curve to the luminance values of the pixels.

Abstract: Aspects of the subject disclosure may include, for example, a method that includes obtaining, by a processing system including a processor, video frames over a network; the processing system uses a machine learning algorithm to identify in each frame a first region comprising a natural image and a second region comprising a synthetic graphic image. The processing system separates the natural image from the synthetic graphic image to generate a natural video and a graphics video, encodes the natural video, and processes the graphics video to generate instructions for rendering graphic images at a client system. The client system performs a decoding procedure for the encoded video, a rendering procedure for client-side graphics in accordance with the instructions, and a compositing procedure to obtain a presentable video stream including the natural image and a client-side graphic corresponding to the synthetic graphic image. Other embodiments are disclosed.

Abstract: A method for viewing pathology images in a web browser is provided.

Abstract: A block of video data is split and coded using existing transform sizes through one of several embodiments. In one embodiment, the block is split in alternate dimensions, depending on the block size. In another embodiment, the video block can be coded after splitting the block into at least two rectangular sub-blocks using horizontal or vertical divisions. Successive divisions using asymmetric splitting are forbidden if an equivalent split can be attained using only symmetrical splitting, and only one succession of divisions is permitted when there are other successions of asymmetric splitting that result in the identical sub-blocks. In another embodiment, a video block is split using successive splits, but the second type of split is dependent on the first type of split. Methods, apparatus, and signal embodiments are provided for encoding and decoding.

Abstract: A method and a motion data extraction and vectorization system (MDEVS) extract and vectorize motion data of an object in motion with optimized data storage and data transmission bandwidth. The MDEVS includes an image sensor, a motion data processor, and a storage unit. The image sensor captures video data including a series of image frames of the object in motion. The motion data processor detects an object in motion from consecutive image frames, extracts motion data of the detected object in motion from each image frame, and generates a matrix of vectors defining the object in motion for each image frame using the extracted motion data. The motion data includes, for example, image data of the object, trajectory data, relative physical dimensions, a type of the object, time stamp of each image frame, etc. The storage unit maintains the generated matrix of vectors for local storage, transmission, and analysis.

Abstract: A semiconductor device and electronic device with reduced power consumption are provided. The semiconductor device includes an encoder, a decoder, and a source driver circuit. An output terminal of the encoder is electrically connected to an input terminal of the source driver circuit, and an output terminal of the source driver circuit is electrically connected to an input terminal of the decoder. The encoder converts input image data into feature-extracted image data, and the decoder restores the feature-extracted image data to the original image data. In addition, provision of a circuit that performs convolution processing using a weight filter for the encoder enables calculation using a convolutional neural network.

Abstract: A pupil detection device includes: a filter weight learner configured to generate a target image on the basis of pupil coordinate data acquired from a learning image and learn weights of a plurality of filters in order to generate a filtered image, by filtering the learning image using the plurality of filters, that is within a predetermined reference range of the target image; a split image generator configured to generate a pupil region split image for an input image using the plurality of filters having the learned weights; and a pupil coordinate detector configured to remove noise of the pupil region split image, select at least one of a plurality of pixels from which noise is removed, and detect pupil coordinates.

Abstract: The invention relates to a method and a device for decoding an image by means of a partition unit comprising an additional region. The method of decoding an image by means of a partition unit comprising an additional region comprises the steps of: partitioning, by reference to a syntax element acquired from a received bit stream, an encoded image, which is included in the bitstream, in at least one partition unit; define an additional region for at least one partition unit; and decoding the encoded image based on the partition unit for which the additional region is defined. The invention improves the image coding efficiency.