Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.

A picture decoding device includes a spatial candidate derivation unit configured to derive a spatial candidate from inter prediction information of a block neighboring a decoding target block and register the derived spatial candidate as a candidate to a first candidate list, a history-based candidate derivation unit configured to generate a second candidate list by adding a history-based candidate included in a history-based candidate list as a candidate to the first candidate list, a candidate selection unit configured to select a selection candidate from candidates included in the second candidate list, and an inter prediction unit configured to perform inter prediction using the selection candidate.

An image coding device including: an edge detecting section configured to perform edge detection using an image signal of a reference image for a coding object block; a transform block setting section configured to set transform blocks by dividing the coding object block such that a boundary between the blocks after division does not include an edge on a basis of a result of the edge detection; and a coding processing section configured to generate coded data by performing processing including an orthogonal transform of each of the transform blocks.

A three-dimensional data encoding method includes: dividing three-dimensional points included in three-dimensional data into three-dimensional point sub-clouds including a first three-dimensional point sub-cloud and a second three-dimensional point sub-cloud; appending first information indicating a space of the first three-dimensional point sub-cloud to a header of the first three-dimensional point sub-cloud, and appending second information indicating a space of the second three-dimensional point sub-cloud to a header of the second three-dimensional point sub-cloud; and encoding the first three-dimensional point sub-cloud and the second three-dimensional point sub-cloud so that the first three-dimensional point sub-cloud and the second three-dimensional point sub-cloud are decodable independently of each other.

According to an embodiment, an image coding method is for coding an image including a luminance component and color difference components. The method includes acquiring a reference image; and generating a predicted image by interpolating the luminance component and the color difference components in the reference image according to a motion vector. If a size of a block, which is designated as a unit of the interpolation, is equal to or smaller than a predetermined first threshold value, the generating includes inhibiting a bi-directional prediction, and performing only a uni-directional prediction to generate the predicted image according to the motion vector.

Disclosed are an intra prediction method of a chrominance block using a luminance sample and an apparatus using the same. An image decoding method comprises the steps of: calculating an intra prediction mode of a chrominance block on the basis of an LM mapping table when the chrominance block uses an LM; and generating a prediction block for the chrominance block on the basis of the calculated intra prediction mode of the chrominance block. When intra prediction mode information of chrominance blocks are decoded, mutually different tables are used depending on whether or not an LM is used, so that encoding and decoding can be performed without an unnecessary waste of bits.

Disclosed herein are exemplary embodiments of innovations in the area of point cloud encoding and decoding. Example embodiments can reduce the computational complexity and/or computational resource usage during 3D video encoding by selectively encoding one or more 3D-point-cloud blocks using an inter-frame coding (e.g., motion compensation) technique that allows for previously encoded/decoded frames to be used in predicting current frames being encoded. Alternatively, one or more 3D-point-cloud block can be encoded using an intra-frame encoding approach. The selection of which encoding mode to use can be based, for example, on a threshold that is evaluated relative to rate-distortion performance for both intra-frame and inter-frame encoding. Still further, embodiments of the disclosed technology can use one or more voxel-distortion-correction filters to correct distortion errors that may occur during voxel compression. Such filters are uniquely adapted for the particular challenges presented when compressing 3D image data. Corresponding decoding techniques are also disclosed.

A method of decoding JVET video, comprising receiving a bitstream indicating how a coding tree unit was partitioned into coding units according to a partitioning structure that allows nodes to be split according to a partitioning technique. An intra direction mode for a coding unit may be selected, as well as one or more of the plurality of reference lines to generate at least one predictor for the intra direction mode. A predictor may be generated from reference samples within each selected reference line by combining predicted pixel values based on a projected position on a main reference line in combination with predicted pixel values based on a projected position on a side reference line. The predicted pixel values are weighted according to a weight parameter, wherein the weight parameter is determined based on a shift conversion factor.

All image-displaying method includes deriving a luminance prediction value, calculating a luminance residual, deriving a chrominance prediction value, calculating a first chrominance residual, deriving a quantized luminance value by quantizing the luminance residual, deriving an inverse quantized luminance value by inverse quantizing the quantized luminance value, selecting one of candidate coefficients as a modification factor, calculating a second chrominance residual by subtracting an adjustment value from the first chrominance residual (wherein the adjustment value is equal to the inverse quantized luminance value multiplied by the modification factor), deriving a quantized chrominance value by quantizing the second chrominance residual, encoding the quantized luminance value and the quantized chrominance value to produce encoded data, decoding the encoded data to obtain decoded image data, and controlling a display device according to the decoded image data to display an image.

A video signal processing method may comprise the steps of: confirming a prediction mode applied to a current coding unit; confirming whether a plurality of preset conditions are satisfied on the basis of at least one of the prediction mode of the current coding unit and a size of the current coding unit; parsing a first syntax element indicating a transform kernel applied to a transform unit included in the current coding unit when the plurality of preset conditions are satisfied; determining a transform kernel applied to horizontal and vertical directions of the current transform unit on the basis of the first syntax element; and generating a residual signal of the current transform unit by performing an inverse transform on the current transform unit using the determined transform kernel.