Abstract: Disclosed herein is an encoding method. The encoding method includes generating multiple feature maps using an input image, transforming the feature maps using a transform vector, and generating a bitstream by performing entropy encoding on at least any one of the feature map, the transform coefficient of the feature map, or the transform vector, or a combination thereof.

Abstract: Provided are an image encoding method and device. When carrying out image encoding for a block within a slice, at least one block in a restored block of the slice is set as a reference block. When this is done, the encoding parameters of the reference block are distinguished, and the block to be encoded is encoded adaptively based on the encoding parameters.

Abstract: Provided is a transform coefficient scan method including: determining a reference transform block for a decoding target block; deriving a scanning map of the decoding target block using scanning information of the reference transform block; and performing inverse scanning on a transform coefficient of the decoding target block using the derived scanning map. According to the present invention, picture encoding/decoding efficiency may be improved.

Abstract: Disclosed herein are a method, an apparatus and a storage medium for processing a feature map. An encoding method for a feature map includes configuring a feature frame for feature maps, and generating encoded information by performing encoding on the feature frame. A decoding method for a feature map includes reconstructing a feature frame by performing decoding on encoded information, and reconstructing feature maps using the feature frame. A feature frame is configured using feature maps, and compression using a video compression codec or a deep learning-based image compression method is applied to the feature frame.

Abstract: A method for decoding an image, the method including receiving a bitstream including image information, decoding base block size information on a size of a base block, and a residual quantization parameter of a decoding object unit, from the bitstream, deriving a predicted quantization parameter of the decoding object unit based on the base block size information, deriving a quantization parameter of the decoding object unit based on the predicted quantization parameter and the residual quantization parameter, and decoding the decoding object unit based on the quantization parameter of the decoding object unit.

Abstract: Provided is a method and apparatus for performing intra-prediction using an adaptive filter. The method for performing intra-prediction includes the steps of: determining whether or not to apply a first filter for a reference pixel value on the basis of information of a neighboring block of a current block; applying the first filter for the reference pixel value when it is determined to apply the first filter; performing intra-prediction on the current block on the basis of the reference pixel value; determining whether or not to apply a second filter for a prediction value according to each prediction mode of the current block, which is predicted by the intra-prediction performance on the basis of the information of the neighboring block; and applying the second filter for the prediction value according to each prediction mode of the current block when it is determined to apply the second filter.

Abstract: Disclosed herein are a video-decoding method and apparatus and a video encoding method and apparatus, and more particularly a method and an apparatus which perform region-differential image encoding/decoding using a recovered image. In accordance with an encoding method according to an embodiment, a recovered low-quality image is generated by performing encoding on an original image and a recovered high-quality image is generated using the recovered low-quality image. An image is segmented into multiple regions, and encoded reconstruction information for generating a reconstructed high-quality image is generated by performing encoding on the image.

Abstract: Disclosed herein is an intra prediction method including: deriving neighbor prediction mode information from a left neighbor prediction mode and an upper neighbor prediction mode; deriving an intra prediction mode for a decoding target unit by using the derived neighbor prediction mode information; and performing intra prediction on the decoding target unit based on the intra prediction mode. According to exemplary embodiments of the present invention, image encoding/decoding efficiency can be improved.

Abstract: Disclosed is a data transmission system that transmits data by using a relay. The relay selects a transmission terminal from among a plurality of terminals accessing a base station. A base station transmits base station data to the relay during a first time slot, and the transmission terminal transmits terminal data to the relay. The relay transmits terminal data to the base station during a second time slot, and transmits base station data to the transmission terminal.

Abstract: Provided is an image encoding/decoding apparatus and method. The image encoding apparatus may include a motion vector prediction unit to perform a prediction with respect to an arbitrary motion vector of a current block within an image, using at least one of vector information of a motion vector corresponding to an adjacent block and vector information of a previous motion vector of the current block, and a differential determination unit to determine differential information of a motion vector of the current block based on the motion vector predicted in the motion vector prediction unit and an actual motion vector of the current block.

Abstract: Disclosed are a method for determining a color difference component quantization parameter and a device using the method. Method for decoding an image can comprise the steps of: decoding a color difference component quantization parameter offset on the basis of size information of a transform unit; and calculating a color difference component quantization parameter index on the basis of the decoded color difference component quantization parameter offset. Therefore, the present invention enables effective quantization by applying different color difference component quantization parameters according to the size of the transform unit when executing the quantization.

Abstract: Disclosed herein is an intra prediction method including: deriving neighbor prediction mode information from a left neighbor prediction mode and an upper neighbor prediction mode; deriving an intra prediction mode for a decoding target unit by using the derived neighbor prediction mode information; and performing intra prediction on the decoding target unit based on the intra prediction mode. According to exemplary embodiments of the present invention, image encoding/decoding efficiency can be improved.

Abstract: A method and apparatus for image compression using a latent variable are provided. The multiple components of the latent variable may be sorted in order of importance. Through sorting, when the feature information of only some of the multiple components is used, the quality of a reconstructed image may be improved. In order to generate a latent variable, the components of which are sorted in order of importance, learning may be performed in various manners. Also, less important information may be eliminated from the latent variable, and processing, such as quantization, may be applied to the latent variable. Through elimination and processing, the amount of data for the latent variable may be reduced.

Abstract: Disclosed are a method for determining a color difference component quantization parameter and a device using the method. Method for decoding an image can comprise the steps of: decoding a color difference component quantization parameter offset on the basis of size information of a transform unit; and calculating a color difference component quantization parameter index on the basis of the decoded color difference component quantization parameter offset. Therefore, the present invention enables effective quantization by applying different color difference component quantization parameters according to the size of the transform unit when executing the quantization.

Abstract: Disclosed are a method for determining a color difference component quantization parameter and a device using the method. Method for decoding an image can comprise the steps of: decoding a color difference component quantization parameter offset on the basis of size information of a transform unit; and calculating a color difference component quantization parameter index on the basis of the decoded color difference component quantization parameter offset. Therefore, the present invention enables effective quantization by applying different color difference component quantization parameters according to the size of the transform unit when executing the quantization.

Abstract: Disclosed herein are a method and apparatus for image compression based on machine learning using a global context. The disclosed image compression network employs an existing image quality enhancement network for an end-to-end joint learning scheme. The image compression network may jointly optimize image compression enhancement and quality enhancement. The image compression networks and image quality enhancement networks may be easily combined within a unified architecture which minimizes total loss, and may be easily jointly optimized.

Abstract: Disclosed herein is a context-adaptive entropy model for end-to-end optimized image compression. The entropy model exploits two types of contexts. The two types of contexts are a bit-consuming context and a bit-free context, respectively, and these contexts are classified depending on the corresponding context requires the allocation of additional bits. Based on these contexts, the entropy model may more accurately estimate the distribution of each latent representation using a more generalized form of entropy models, thus improving compression performance.

Abstract: An intra prediction method according to the present invention comprises the following steps: performing a directional prediction using at least one of a neighboring pixel of a current block and a left upper corner pixel positioned at a left upper corner of the current block so as to obtain a first prediction value for the current block; obtaining a second prediction value for the current block using the reference sample positioned in the current block; and weighted summing the first prediction value and the second prediction value using a weighting matrix so as to obtain a final prediction value for the current block. According to the present invention, image encoding/decoding efficiency may be improved.

Abstract: The present invention relates to an apparatus and method for encoding and decoding an image by skip encoding. The image-encoding method by skip encoding, which performs intra-prediction, comprises: performing a filtering operation on the signal which is reconstructed prior to an encoding object signal in an encoding object image; using the filtered reconstructed signal to generate a prediction signal for the encoding object signal; setting the generated prediction signal as a reconstruction signal for the encoding object signal; and not encoding the residual signal which can be generated on the basis of the difference between the encoding object signal and the prediction signal, thereby performing skip encoding on the encoding object signal.

Abstract: Provided is a scalable video-decoding method based on multiple layers. The scalable video-decoding method according to the present invention comprises: a step of predicting first filter information of a video to be filtered using the information contained in an object layer and/or information contained in another layer, and generating second filter information in accordance with the prediction; and a step of filtering the video to be filtered using the second filter information. According to the present invention, the amount of information being transmitted is reduced, and video compression performance is improved.