Abstract: A method of video processing includes determining, for a conversion between a current block of a video and a coded representation of the video, that a resolution of a current picture containing the current block and a reference picture used for the conversion are different, and performing the conversion based on the determining such that predicted values of a group of samples of the current block are generated using a horizontal or a vertical interpolation filter.

Abstract: Disclosed are region-based image encoding/decoding method and apparatus. The method of decoding an image includes: determining a projection format of a 360-degree video image; determining, on the basis of the determined projection format, a spatial correlation degree between a current block and a neighboring block; and determining, on the basis of the determined spatial correlation degree, a candidate block for predicting the current block.

Abstract: Provided is a video decoding method including obtaining, from a bitstream, split information indicating whether a current block is to be split; when the split information does not indicate that the current block is to be split, decoding the current block according to encoding information about the current block; and when the split information indicates that the current block is to be split, splitting the current block into at least two lower blocks, obtaining encoding order information indicating an encoding order of the at least two lower blocks of the current block from the bitstream, determining a decoding order of the at least two lower blocks according to the encoding order information, and decoding the at least two lower blocks according to the decoding order.

Abstract: Method, apparatus and systems are disclosed. In one embodiment, a method of decoding includes obtaining a sub-block based motion prediction signal for a current block of the video; obtaining one or more spatial gradients of the sub-block based motion prediction signal or one or more motion vector difference values; obtaining a refinement signal for the current block based on the one or more obtained spatial gradients or the one or more obtained motion vector difference values; obtaining a refined motion prediction signal for the current block based on the sub-block based motion prediction signal and the refinement signal; and decoding the current block based on the refined motion prediction signal.

Abstract: A method of video processing are described. The method includes determining, for a conversion between a video region of a picture of a video and a coded representation of the video, enablement status of a coding tool used to represent the video region in the coded representation; and performing the conversion according to the determination; wherein a first flag is included in a picture header to indicate the enablement status of the coding tool for the picture.

Abstract: A method of decoding video data may comprise decoding data from an encoded bitstream to generate motion vectors and performing a decoder-side motion vector refinement (DMVR) process on one or more of the motion vectors. Performing the DMVR process may include determining one or more characteristics of current video block being decoded and determining a search area for the DMVR process for the current video block based on the determined one or more characteristics of the current video block.

Abstract: A load in processing of searching for a motion vector is reduced. In order to solve the problem described above, a motion vector derivation apparatus according to one aspect of the present invention that derives a motion vector to be referred to for generating a prediction image to be used for coding or decoding of a video includes a motion vector search unit configured to search for a motion vector on a prediction unit basis through matching processing. The motion vector search unit is configured to stop search of the motion vector, depending on whether or not a conditional expression according to a pixel bit-depth is satisfied.

Abstract: A method of video processing includes determining, for a conversion between a current block of a video and a coded representation of the video, that a resolution of a current picture containing the current block and a reference picture used for the conversion are different, and performing the conversion based on the determining such that predicted values of a group of samples of the current block are generated using a horizontal or a vertical interpolation filter.

Abstract: An encoder includes processing circuitry and a memory coupled to the processing circuitry. The processing circuitry is configured to: select a filter based at least on a prediction mode used for a first block, the filter including first filter coefficients for the first block and second filter coefficients for a second block; multiply values of first pixels among the first block and second pixels among the second block by the first filter coefficients to change a value of a first pixel in the first pixels; and multiply the values of the first pixels among the first block and the second pixels among the second block by the second filter coefficients to change a value of a second pixel in the second pixels.

Abstract: A video processing method, comprising: initializing a HMVP list for a current CTU row when the current CTU is the beginning CTU of a current CTU row; and processing the current CTU row based on the HMVP list. By performing the method, the encoding efficiency and decoding efficiency are improved.

Abstract: The present disclosure relates to an image decoding and encoding method which can efficiently perform inter-prediction by applying a regular merge mode to the current block on the basis of the case in which an MMVD mode, a merge sub-block mode, a CIIP mode, and a partitioning mode, in which prediction is performed by dividing the current block into two partitions, are not available for the current block.

Abstract: In communication applications, aggregate source image data at a transmitter exceeds the data that is needed to display a rendering of a viewport at a receiver. Improved streaming techniques that include estimating a location of a viewport at a future time. According to such techniques, the viewport may represent a portion of an image from a multi-directional video to be displayed at the future time, and tile(s) of the image may be identified in which the viewport is estimated to be located. In these techniques, the image data of tile(s) in which the viewport is estimated to be located may be requested at a first service tier, and the other tile in which the viewport is not estimated to be located may be requested at a second service tier, lower than the first service tier.

Abstract: Methods, devices and systems for intra-block coding based decoding or encoding of video while using block vector signaling and/or merge candidates are disclosed. An example method for video processing includes performing a conversion between a video region of a video and a bitstream representation of the video, wherein the bitstream representation selectively includes motion vector difference (MVD) related syntax elements for an intra block copy (IBC) advanced motion vector prediction (AMVP) mode based on a maximum number of a first type of IBC candidates used during the conversion of the video region, wherein, when an IBC mode is applied, samples of the video region are predicted from other samples in a video picture corresponding to the video region.

Abstract: Techniques for time-based memory allocation for a neural network inference are disclosed. A description of a neural network comprising a plurality of operations to be executed across a set of accelerators is received. A plurality of interconnect times at a plurality of partition points within the neural network are calculated. Each of the plurality of interconnect times corresponds to a duration of time for transferring an output feature map from one of the set of accelerators to another of the set of accelerators to be used as an input feature map. A partitioning scheme that divides the plurality of operations into a set of subgraphs is determined based on the plurality of interconnect times. Each of the set of subgraphs is assigned to a different accelerator of the set of accelerators in accordance with the partitioning scheme.

Abstract: An electronic device can include a first image sensor configured to capture a first image of a field of view and a second image sensor configured to capture a second image of the field of view. The electronic device can include a color filter adjacent to the second image sensor such that the field of view is viewable by the second image sensor through the color filter. The first image can have a first pixel resolution. The second image can have a second pixel resolution. The electronic device can include a controller configured to determine a third image based on luminance content of the first image and color content of the second image. The third image can have a third pixel resolution indicative of a spatial resolution of the first image and a spectral resolution of the second image.

Abstract: Techniques are described of using Position Dependent Intra Prediction Combination (PDPC). A video coder such as a video encoder or a video decoder utilizes PDPC in cases where a current block intra mode predicted using an angular intra prediction mode.

Abstract: An image region segmentation method and system suing self-spatial adaptive normalization is provided. The image region segmentation system includes: an encoder configured to encode an image for segmenting a region by using a plurality of encoding blocks; and a decoder configured to decode the image encoded by the encoder and to generate a region-segmented image by using a plurality of decoding blocks, wherein each of the encoding blocks processes an inputted image into a convolution layer, performs spatial adaptive normalization, and then reduces the image and delivers the image to the next encoding block. Accordingly, spatial characteristics of the image are considered in an encoding process and a decoding process, so that region segmentation can be exactly performed with respect to various images.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an artificial neural network architecture based on a synaptic connectivity graph. According to one aspect, there is provided a method comprising: obtaining a synaptic resolution image of at least a portion of a brain of a biological organism; processing the image to identify: (i) a plurality of neurons in the brain, and (ii) a plurality of synaptic connections between pairs of neurons in the brain; generating data defining a graph representing synaptic connectivity between the neurons in the brain; determining an artificial neural network architecture corresponding to the graph representing the synaptic connectivity between the neurons in the brain; and processing a network input using an artificial neural network having the artificial neural network architecture to generate a network output.

Abstract: Method and apparatus for encoding and decoding prediction residues in a video coding system also disclosed. At the decoder side, a Rice parameter for the target transform coefficient is determined based on a local sum of absolute levels of neighboring transform coefficients of the target transform coefficient. A dependent quantization state is determined and a zero-position variable is determined based on the dependent quantization state and the Rice parameter. One or more coded bits associated with a first syntax element for the target transform coefficient in a transform block are parsed and decoded using one or more codes including a Golomb-Rice code with the Rice parameter, where the first syntax element corresponds to a modified absolute level value of the target transform coefficient. An absolute level value of the target transform coefficient is derived according to the zero-position variable and the first syntax element.

Abstract: A method of a geometry merge mode for point cloud coding (PCC), is performed by at least one processor, and includes obtaining a candidate node of an octree partition of a point cloud, for a current node of the octree partition, the current node being currently-coded, and the candidate node being previously-coded. The method further includes obtaining an occupancy code of the obtained candidate node, constructing a candidate list including the obtained occupancy code of the candidate node, obtaining an occupancy code of the current node, based on the constructed candidate list, and performing the PCC, based on the obtained occupancy code of the current node.