Abstract: Methods, devices and systems for configuring different access units in scalable video coding are described. In one example aspect, a method of video processing include performing a conversion between a video including one or more pictures in one or more video layers and a bitstream of a video. The bitstream includes a coded video sequence that includes one or more access units. The bitstream conforms to a format rule that specifies that each access unit of the one or more access units that is a gradual decoding refresh access unit includes exactly one picture for each video layer present in the coded video sequence.

Abstract: Interpolation between explicitly signaled CPB (or HRD) parameters at selected bit rates is used to achieve a good compromise between CPB parameter transmission capacity and CPB parametrization effectiveness and may be, particularly, made in an effective manner.

Abstract: Interpolation between explicitly signaled CPB (or HRD) parameters at selected bit rates is used to achieve a good compromise between CPB parameter transmission capacity and CPB parametrization effectiveness and may be, particularly, made in an effective manner.

Abstract: An inter prediction method according to the present invention comprises the steps of: selecting candidate units from among reconstructed neighbor units; creating a candidate unit set with respect to units to be decoded, using the selected candidate units; determining a reference unit from among the candidate units which constitute the created candidate unit set; and performing inter prediction on the units to be decoded, using the determined reference unit. According to the present invention, image encoding/decoding efficiency can be improved.

Abstract: Methods and apparatus for video processing, including coding and decoding, are described. One example video processing method includes performing a conversion between a video having one or more video layers and a bitstream of the video according to a format rule, and wherein the format rule specifies that a value of a variable indicating whether to output a picture in an access unit is determined based on a flag indicating whether to output another picture in the access unit.

Abstract: Techniques are described for processing video data, such as by performing learned bidirectional coding using a unidirectional coding system and an interpolated reference frame. For example, a process can include obtaining a first reference frame and a second reference frame. The process can include generating a third reference frame at least in part by performing interpolation between the first reference frame and the second reference frame. The process can include performing unidirectional inter-prediction on an input frame based on the third reference frame, such as by estimating motion between an input frame and the third reference frame, and generating a warped frame at least in part by warping one or more pixels of the third reference frame based on the estimated motion. The process can include generating, based on the warped frame and a predicted residual, a reconstructed frame representing the input frame, the reconstructed frame including a bidirectionally-predicted frame.

Abstract: This application discloses image coding methods and apparatuses. One method comprises obtaining a plurality of groups of human skeleton data associated with performing an action by a human body, wherein each group of the plurality of groups of human skeleton data comprises joint data associated with a joint for performing the action. Based on joint data comprised in at least a portion of the plurality of groups of human skeleton data, a motion feature corresponding to the plurality of groups of human skeleton data is extracted, and the motion feature is encoded to obtain a motion feature image.

Abstract: Methods, systems and devices for implementing constraints used in video encoding and video decoding are described. An example method of video processing includes performing a conversion between a video including one or more pictures including one or more slices and a bitstream of the video, wherein the bitstream is organized into a plurality of access units (AUs), AU 0 to AU n, based on a format rule, where n is a positive integer, wherein the format rule specifies a relationship between removal times of each of the plurality of AUs from a coded picture buffer (CPB) during decoding and a number of slices in the each of the plurality of AUs.

Abstract: An image signal decoding method according to an embodiment of the present disclosure comprises the steps of: partitioning the current picture into a plurality of tiles; decoding partition information indicating a slice type, the partition information indicating whether a rectangular slice is to be applied; determining the number of slices in the current picture; and defining the slices using the tiles.

Abstract: Provided is a photoelectric conversion device including: at least one charge holding portion including a first semiconductor region of a first conductivity type and configured to hold signal charges based on incident light; and an avalanche photodiode including a second semiconductor region of the first conductivity type, in which the signal charges are transferred from the first semiconductor region to the second semiconductor region via a third semiconductor region of a second conductivity type that is different from the first conductivity type, a fourth semiconductor region of the first conductivity type, and a fifth semiconductor region of the second conductivity type in this order.

Abstract: A method for video coding is provided. The method may include: identifying motion vectors (MVs) and control point motion vectors (CPMVs) for spatial MV prediction and affine motion inheritance, respectively; converting the MVs and the CPMVs into a mantissa-exponent format; and storing mantissa-exponent representations of the MVs and the CPMVs in a memory.

Abstract: Methods and apparatus for video processing, including coding and decoding, are described. One example video processing method includes performing a conversion between a video having one or more video layers and a bitstream of the video according to a format rule, and wherein the format rule specifies that a value of a variable indicating whether to output a picture in an access unit is determined based on a flag indicating whether to output another picture in the access unit.

Abstract: An encoder includes circuitry and memory. The circuitry, using the memory: derives a one-dimensional array of a plurality of reference samples for intra prediction; performs smoothing on the one-dimensional array of the plurality of reference samples which has been derived; and generates a prediction image using the plurality of reference samples. In deriving the one-dimensional array, the circuitry projects a value of at least one decoded pixel located on a first line onto a second line perpendicular to the first line, to derive at least one of the plurality of reference samples, and the smoothing is performed on the at least one decoded pixel projected onto the second line.

Abstract: A method and device for controlling coding tools are provided. The video decoding method includes decoding, from a high level of a bitstream, an enable flag indicating whether one or more coding tools are enabled. The coding tools includes a first coding tool that encodes sample values using luma component mapping based on a piecewise linear model. The method includes acquiring a value of an application flag depending on a value of the enable flag, by setting the application flag indicating whether to apply the coding tools to a predetermined value, or by decoding the application flag from a low level of the bitstream, the application flag including a first application flag indicating whether to apply the first coding tool. The coding tools are operated when the value of the application flag is a value indicating that the coding tools are applied.

Abstract: A method and device for controlling coding tools are provided. The video decoding method includes decoding, from a high level of a bitstream, an enable flag indicating whether one or more coding tools are enabled. The coding tools includes a first coding tool that encodes sample values using luma component mapping based on a piecewise linear model. The method includes acquiring a value of an application flag depending on a value of the enable flag, by setting the application flag indicating whether to apply the coding tools to a predetermined value, or by decoding the application flag from a low level of the bitstream, the application flag including a first application flag indicating whether to apply the first coding tool. The coding tools are operated when the value of the application flag is a value indicating that the coding tools are applied.

Abstract: An encoding method is performed by an encoding apparatus, and the encoding method includes a step in which an image of an object captured by a camera in a plurality of frames of a moving image is analyzed and it is determined whether camera parameters relating to an intrinsic matrix of the camera are invariable, a step in which, when the camera parameters are invariable, six parameters representing destinations of three points for a projective transformation unit of the image of the object are generated, and a homography matrix is generated on the basis of the six parameters, and a step in which projective transformation is performed on the projective transformation unit of the image of the object using the homography matrix, and a prediction signal of the image of the object is generated on the basis of the result of the projective transformation.

Abstract: A method for decoding a compressed video bit stream in a video decoder to recover a video sequence, the video decoder including a plurality of decoder processing cores is provided. The method includes determining that a picture is encoded in the compressed bit stream as a pre-determined number of independently encoded sub-pictures, and dispatching a first encoded sub-picture of the pre-determined number of sub-pictures to a first decoder processing core of the plurality of decoder processing cores and a second encoded sub-picture of the pre-determined number of sub-pictures to a second decoder processing core of the plurality of decoder processing cores, wherein the first encoded sub-picture and the second encoded sub-picture are independently decoded in parallel on the respective first and second decoder processing cores.

Abstract: Pulsed hyperspectral, fluorescence, and laser mapping imaging in a light deficient environment is disclosed. A system includes an emitter for emitting pulses of electromagnetic radiation and an image sensor comprising a pixel array for sensing reflected electromagnetic radiation. The system includes a controller configured to synchronize timing of the emitter and the image sensor. The system is such that at least a portion of the pulses of electromagnetic radiation emitted by the emitter comprises one or more of a hyperspectral emission, a fluorescence emission, or a laser mapping pattern.

Abstract: A video encoding apparatus includes a first processor and at least two encoders. The first processor is configured to divide a sequence of video frames into M first groups of pictures (GOPs) and send the M first GOPs to the at least two encoders, M being an integer greater than 1. The at least two encoders are configured to perform parallel encoding on the received M first GOPs to obtain M groups of video encoded data and send the M groups of video encoded data to the first processor. The first processor is further configured to merge the M groups of video encoded data into a video data stream.

Abstract: An information processing apparatus includes processors configured to execute inference processing using a GPU on frames of a moving image through each application for each of a plurality of applications, acquire a first degree of similarity between a target frame and a frame at a time of execution of previous inference processing, acquire a second degree of similarity between the target frame and an immediately preceding frame that is executed after the previous inference processing, set a constraint on execution of inference processing for the target frame having a throughput larger than a certain value when a number of frames accumulated in a queue that is used for waiting for the execution of the inference processing and accumulates frames exceeds a certain number, and determine whether to execute the inference processing for the target frame based on the first degree, the second degree, and whether the constraint presents.