Abstract: A motion vector for a current block of a current frame is decoded from a compressed bitstream. A location of a reference block within an un-generated reference frame is identified. The reference block is generated using a forward reference frame and a backward reference frame without generating the un-generated reference frame. The reference block is generated by identifying an extended reference block by extending the reference block at each boundary of the reference block by a number of pixels related to a filter length of a filter used in sub-pixel interpolation; and generating pixel values of only the extended reference block by performing a projection using the forward reference frame and the backward reference frame without generating the whole of the un-generated reference frame. The current block is then decoded based on the reference block and the motion vector.

Abstract: An image decoding method performed by means of a decoding device according to the present invention comprises the steps of: deriving quantized transform coefficients with respect to a target block from a bitstream; performing inverse quantization with respect to the quantized transform coefficients with respect to the target block and deriving transform coefficients; deriving residual samples with respect to the target block on the basis of reduced inverse transform with respect to the transform coefficients; and generating a reconstructed picture on the basis of the residual samples with respect to the target block and prediction samples with respect to the target block. The reduced inverse transform is performed on the basis of a reduced inverse transform matrix. The reduced inverse transform matrix is a non-square matrix of which the number of columns is smaller than the number of rows.

Abstract: An encoder includes circuitry and memory connected to the circuitry. In operation, the circuitry: corrects a base motion vector using a correction value for correcting the base motion vector in a predetermined direction; and encodes a current partition to be encoded in an image of a video, using the base motion vector corrected. The correction value is specified by a first parameter and a second parameter, the first parameter indicating a table to be selected from among a plurality of tables each including values, the second parameter indicating one of the values included in the table to be selected indicated by the first parameter. In each of the plurality of tables, a smaller value among the values is assigned a smaller index. Each of the plurality of tables includes a different minimum value among the values.

Abstract: An image decoding method performed by a decoding device according to the present document comprises the steps of: deriving a context model for a sign flag of a current residual coefficient of a current block; and decoding the sign flag on the basis of the context model, wherein the context model for the sign flag is derived on the basis of a sign flag of a residual coefficient decoded before the current residual coefficient in the current block.

Abstract: An image compression method includes: obtaining a target image and a target code rate corresponding to the target image; determining a first code rate parameter corresponding to the target code rate; and inputting the target image and the first code rate parameter into an image compression model, that has been trained, for processing to obtain a compressed image with the target code rate, wherein the image compression model is obtained by training an initial image compression model based on multiple code rate parameters including the first code rate parameter.

Abstract: The present invention discloses a method for encoding/decoding a video signal and an apparatus for the method. More specifically, a method for decoding a video signal comprises generating a residual block of a current block by performing entropy decoding on the video signal; if size of the current block is smaller than a predetermined first size, parsing a transform skip flag which indicates whether a transform skip is applied to the current block; determining whether to parse a primary transform flag which indicates whether a primary transform is applied to the current block; if it is determined to parse the primary transform flag, parsing the primary transform flag; and if the primary transform flag indicates that a primary transform is applied to the current block, generating a primary inverse transformed transform block of the current block by performing a primary inverse transform to the residual block.

Abstract: A focusing method of a camera for obtaining an image of a surveillance area by performing a pan-tilt-zoom (PTZ) operation is included. The focusing method includes: determining whether a region of interest set in the surveillance area is included in a first image obtained by the camera; converting a mode according to a result of the determination by selecting a first mode in which focusing is performed using a first focusing algorithm or a second mode in which focusing is performed using a second focusing algorithm that is different from the first focusing algorithm; and focusing the camera with respect to the first image according to the first mode or the second mode.

Abstract: A system and method for frost detection and frost mitigation for an imaging device within a container interior. According to a first preferred embodiment, the system preferably may include an imaging device having one or more LED light sources for illuminating the container interior. According to a preferred embodiment, the system may preferably first receive digital images from the imaging device along with one or more detected sensor inputs. Thereafter, the system may preferably calculate the potential for frost on or around the imaging device based on one or more sensor inputs which may include the imaging device temperature in combination with a door open signal, a detected light level or the like. The system may then preferably analyze the digital images during times of likely frost events using a frost detection algorithm which detects the presence of frost based on image characteristics derived from previously captured images with known frost levels.

Abstract: Embodiments of the present disclosure provide an encoding and decoding method, apparatus and device.

Abstract: An image encoding/decoding method and apparatus are provided. An image decoding method according to the present disclosure may comprise constructing an affine merge candidate list for a current block, based on an inter prediction mode of the current block being an affine merge mode, selecting one affine merge candidate from the affine merge candidate list, deriving motion information of the current block based on motion information of the selected affine merge candidate, generating a prediction block of the current block based on the motion information of the current block, and reconstructing the current block based on the prediction block of the current block. The constructing the affine merge candidate list may comprise deriving a constructed affine merge candidate, and the deriving the constructed affine merge candidate may comprise deriving a weight index for bi-prediction of the constructed affine merge candidate.

Abstract: An encoder includes circuitry and memory connected to the circuitry. In operation, the circuitry corrects a base motion vector using a correction value in a fixed direction; and encodes a current partition by using the corrected base motion vector corrected. The correction value is specified by an index indicating one of correction values included in a table. The table is selected from among a plurality of tables, wherein the correction values in one of the plurality of tables have different increments from the correction values in another one of the plurality of tables.

Abstract: An image encoding/decoding method and apparatus for performing template matching-based intra prediction are provided. An image decoding method may comprise deriving a first intra-prediction mode for a current block, generating a first intra-prediction block corresponding to the first intra-prediction mode, deriving a second intra-prediction mode for the current block, generating a second intra-prediction block corresponding to the second intra-prediction mode, and generating a final intra-prediction block by using a weighted sum of the first intra-prediction block and the second intra-prediction block.

Abstract: The present invention provides an image encoding method and an image decoding method. The image decoding method of the present invention may comprise: obtaining intra-frame prediction information of a current block from a bitstream; inducing an intra-frame prediction mode of the current block on the basis of the intra-frame prediction information; determining a reference region for intra-frame prediction of the current block; and performing intra-frame prediction of the current block on the basis of the intra-frame prediction mode and the reference region.

Abstract: Methods and apparatus are provided for improved chroma encoding and decoding. An apparatus includes an encoder for encoding picture data for at least a block in a picture. Multiple partition types are supported for intra chroma coding of the block. The multiple partition types include a set of chroma partition types and a set of luma partition types. The set of chroma partition types are different than the set of luma partition types.

Abstract: An image decoding method according to the present document may comprise: a step for deriving an inter prediction mode from encoded information; a step for constructing reference pictures lists; a step for deriving motion information including reference picture indices for symmetric motion vector differences (SMVD) on the basis of reference pictures included in the reference picture lists; and a step for generating prediction samples on the basis of the motion information. The reference picture indices for SMVD may be derived on the basis of short-term reference pictures included in the reference picture lists.

Abstract: According to the disclosure of the present document, when the inter-prediction type of the current block indicates biprediction, weight index information for a candidate in a merge candidate list or sub-block merge candidate list can be derived, and coding efficiency can be raised.

Abstract: The present invention relates to a method for signaling image information and to a decoding method using same. The method for signaling image information according to the present invention comprises: a step of performing inter-prediction for a current picture; and a step of signaling information including the result of said inter-prediction and reference picture information indicating reference pictures usable in said inter prediction, wherein said reference picture information contains pieces of picture order count (POC) information of said usable reference pictures. The POC information of said usable reference pictures in said reference picture information is configured such that POCs for the pictures existing before said current picture in terms of a POC sequence are located at the front, and POCs for the pictures existing after said current picture in terms of a POC sequence are located following the POCs located at the front.

Abstract: A visual media processing method includes determining, for a conversion between a first video block of a visual media data and a bitstream representation of the visual media data, an availability of a second video block of the visual media data using a rule; and performing the conversion based on the determining, wherein the rule is at least based on a coding mode used for coding the first video block into the bitstream representation, wherein the rule specifies disallowing motion information of the second video block from being used in a merge list construction of the first block by treating the second video block as unavailable.

Abstract: This disclosure relates to a harmonized design among multiple reference line intra prediction, transform partitioning, and transform kernels or processing video information. One example method is disclosed. The method includes retrieving a data block of a video frame, the data block having an adjacent reference line and one or more non-adjacent reference lines in the video frame; determining whether one of the one or more non-adjacent reference lines is to be used for intra prediction of the data block. When an adjacent reference line is used for the intra prediction of the data block, selecting a target transform kernel from a first set of transform kernels to transform the data block; and when a non-adjacent reference line is used for the intra prediction of the data block, selecting the target transform kernel from a second set of transform kernels to transform the data block.

Abstract: Provided is an encoder including circuitry and memory coupled to the circuitry. A prediction mode for a current block is an affine mode, and in operation, the circuitry: derives a base motion vector which is a motion vector to be used in a prediction process for the current block, and is a motion vector at an affine-mode control point in the current block; 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; if so, modifies a second motion vector different from the base motion vector and the first motion vector, and if not, does not modify the second motion vector; and encodes the current block using the second motion vector modified or the second motion vector not modified.