Abstract: Provided are methods of encoding and decoding a multiview video by performing inter-prediction and inter-view prediction on each view image of the multiview video. A method of prediction-encoding the multiview video includes determining at least one reference picture list from among first and second reference picture lists which respectively include restored images having a viewpoint of a current picture for inter-prediction of the current picture and restored images for inter-view prediction; determining at least one reference picture and reference block with respect to a current block of the current picture by using the determined at least one reference picture list; and performing at least one selected from inter-prediction and inter-view prediction on the current block by using the reference block.

Abstract: A multi-layer video decoding method includes receiving a plurality of multi-layer image streams that constitute a multi-layer video, obtaining, from a data unit header including information of a second random access point (RAP) picture that corresponds to a first RAP picture included in a first layer image stream and is included in a second layer image stream from among the plurality of multi-layer image streams, first picture order count (POC) information for determining a first partial value of a POC of the second RAP picture that is set to be the same as a POC of the first RAP picture, obtaining, from the data unit header, second POC information about a second partial value of the POC of the second RAP picture, and obtaining the POC of the second RAP picture by using the first POC information and the second POC information.

Abstract: A multi-view video encoding method multiplexes an encoded multi-view image by a predetermined data unit and adds a scalable extension type (SET) indicating which view of image among a basic view image and an additional view image is related to data included in the predetermined data unit, a depth flag indicating which image is related to the data among a texture image and a depth map image, and a view ID of the data to a header of the predetermined data unit.

Abstract: Provided are multiview video inter-layer encoding and decoding based on coding units of a tree structure. A video encoding method includes operations of encoding a base layer image that is one of a base view texture image and a base view depth image of a base view image, based on coding units of a tree structure that are among coding units obtained by hierarchically splitting a maximum coding unit of an image, determining an inter-layer encoding mode for performing inter-layer encoding on an additional view image by referring to the base layer image based on the coding units of the tree structure, and referring to an additional layer image including the additional view image, based on the inter-layer encoding mode.

Abstract: Provided are a method and apparatus for decoding a multiview video and a method and apparatus for encoding a multiview video. The decoding method includes: receiving multiview image streams that configure the multiview video; obtaining, from a predetermined data unit header that includes information of a base-view picture included in a base-view image stream, picture order count (POC) information of the base-view picture; determining, using the POC information of the base-view picture, a POC of the base-view picture, based on an instantaneous decoding refresh (IDR) picture of a base-view; and determining, using the POC of the base-view picture, a POC of an additional-view picture that is included in a same access unit as the base-view picture and is transmitted.

Abstract: Provided are methods and apparatuses for encoding and decoding a multiview video. The method of decoding the multiview video includes obtaining a data unit including encoding information of texture pictures and depth map pictures of a multiview image related to a same point of time, obtaining, from the data unit, view information of pictures that are encoded and are included in the data unit, type information indicating a type of each of the pictures from among the texture pictures and the depth map pictures, and reference flag information indicating whether each of the pictures is previously inter-layer predicted by referring to a texture picture of the same point of time or to a depth map picture of the same point of time, determining an encoding order of the pictures, based on the obtained information, and decoding the texture pictures and depth map pictures based on the determined encoding order.

Abstract: Provided are scalable video encoding and decoding methods and apparatuses. A scalable video encoding method includes: encoding a lower layer image according to coding units having a tree structure, the coding units hierarchically split from maximum coding units of an image; determining scalable coding modes for performing scalable encoding on a higher layer image based on the coding units having the tree structure by referring to the lower layer image; predicting and encoding the higher layer image by referring to encoding information of the lower layer image based on the determined scalable coding modes; and outputting coding modes, predicted values of the lower layer image, and the determined scalable coding modes of the higher layer image based on the determined scalable coding modes.

Abstract: A multiview video decoding method includes receiving a base view image stream of a base viewpoint and additional view image streams of at least two additional viewpoints, restoring base view images by performing motion compensation that references base view anchor pictures of an I-picture type, by using the base view image stream, restoring a view decoding refresh image configured for viewpoint switching for changing a first additional viewpoint, by performing disparity compensation that references at least one of the restored base view images, on a first additional view image stream, and restoring first additional view images of the first additional viewpoint by performing at least one of disparity compensation that references the restored base view images and motion compensation that references restored images of the first additional viewpoint excluding the view decoding refresh image that precedes the restored first additional view images, on the first additional view image stream.

Abstract: Provided are a video encoding method and a video decoding method according to spatial subdivisions based on splitting a picture into a first tile and a second tile, and splitting a current tile among the first tile and the second tile into at least one slice segment, encoding the first tile and the second tile, independently from each other, and encoding maximum coding units of a current slice segment among the at least one slice segment included in the current tile, with respect to the at least one slice segment included in the current tile.

Abstract: Disclosed are a scalable video encoding method and apparatus and a scalable video decoding method and apparatus. The scalable video encoding method adds, into a bitstream, table index information representing one of a plurality of scalable extension type information tables in which available combinations of a plurality of scalable extension types are specified and layer index information representing the scalable extension type of the encoded video among combinations of a plurality of scalable extension types included in a scalable extension type information table.

Abstract: Video encoding and decoding accompanying inter prediction and motion compensation in a multi-view video prediction structure. A multi-view video prediction restoring method includes receiving a base view image stream and additional view image streams for two or more additional views; restoring base view images including base view anchor pictures that are I-picture type images by performing motion compensation referring to the base view images by using the base view image stream; and restoring images of a first additional view by performing at least one of disparity compensation referring to the restored base view images and motion compensation referring to images except for an anchor picture having a preceding reproduction order among the images of the first additional view by using an image stream of the first additional view among the additional view image streams.

Abstract: A video encoding method includes: generating encoding symbols by performing source coding on subregions formed by splitting a picture in a vertical direction, based on blocks having a predetermined size; determining a reference block to be referred to for determining code probability information of a start block in a current subregion, the reference block being determined from among boundary blocks of a neighboring subregion which are encoded before the start block and adjacent to a boundary between the current subregion and the neighboring subregion; performing entropy encoding on blocks of the current subregion, starting from the start block, by using the encoding symbols of the blocks of the current subregion based on the code probability information of the start block determined by using code probability information of the determined reference block; and performing entropy encoding on another subregion in parallel with performing entropy encoding on the current subregion.

Abstract: A multi-view video prediction method and a multi-view video prediction restoring method. The multi-view video prediction method includes generating a base layer image stream including residual values of I-picture base view key pictures and base view images of a base view by performing inter prediction between the base view images; and generating an enhancement layer image stream comprising residual values of additional view images of an additional view by performing inter-view prediction for predicting the additional view images with reference to the base view images, performing inter prediction for predicting a different additional view key picture with reference to an additional view key picture from among the additional view images, and performing inter prediction for predicting an additional view image other than the additional view key picture with reference to the additional view images.

Abstract: Provided are a method and apparatus for interpolating an image. The method includes: selecting a first filter, from among a plurality of different filters, for interpolating between pixel values of integer pixel units, according to an interpolation location; and generating at least one pixel value of at least one fractional pixel unit by interpolating between the pixel values of the integer pixel units by using the selected first filter.

Abstract: A method and apparatus for decoding the depth map of multi-view video data are provided. The method includes splitting a block of restored multi-view color video frame into a partition based on a pixel value of the block of the prediction-encoded and restored multi-view color video frame; obtaining a parameter indicating correlation between block partitions of the multi-view color video frame and block partitions of the depth map frame using peripheral pixel values of the block partitions of the multi-view color video frame and peripheral pixel values of the block partitions of the depth map frame corresponding to the block partitions of the multi-view color video frame with respect to each of the block partitions of the restored multi-view color video frame; and obtaining prediction values of corresponding block partitions of the depth map frame from the block partitions of the restored multi-view color video frame using the obtained parameter.

Abstract: A method and apparatus for encoding multi-view video data and a method and apparatus for decoding multi-view video data are provided. The method of encoding multi-view video data includes obtaining a multi-view color video frame and a depth map frame corresponding to the multi-view color video frame, prediction-encoding the multi-view color video frame, and prediction-encoding the depth map frame, based on a result of prediction-encoding the multi-view color video frame.

Abstract: Provided are a method and apparatus for interpolating an image. The method includes: selecting a first filter, from among a plurality of different filters, for interpolating between pixel values of integer pixel units, according to an interpolation location; and generating at least one pixel value of at least one fractional pixel unit by interpolating between the pixel values of the integer pixel units by using the selected first filter.

Abstract: Provided are methods and apparatuses for encoding and decoding a motion vector in a multi-view view image sequence. A method of encoding includes: determining a view direction motion vector of a current block by performing motion prediction on the current block with reference to a first frame having a second view that is different from a first view of the current block; determining view direction motion vector predictor candidates using a view direction motion vector of an adjacent block that refers to a reference frame having a different view from the first view, and a view direction motion vector of a corresponding region included in a second reference frame having the first view and a different picture order count than the current frame; and encoding a difference value between the view direction motion vector of the current block and a selected view direction motion vector predictor, and mode information.

Abstract: Methods for scalable video encoding and decoding for a multi-view video and apparatuses for scalable video encoding and decoding which implement the methods are provided. At least one root image and other remaining images of an image sequence of a video are classified into a plurality of layers. At least one reference image relating to a current image of the image sequence is generated by using a parent image of the current image based on a reference image conversion technique for scalable prediction encoding. Prediction encoding may be performed with respect to the current image by using the at least one reference image.

Abstract: Provided are methods and apparatuses for encoding and decoding an image by using adaptive filtering. The method of encoding an image by using adaptive filtering includes: determining a filter to be applied to a reference frame used for prediction encoding of a current block to be encoded, by adaptively changing a size and filter coefficients of the filter; filtering the reference frame by using the determined filter; prediction encoding the current block by using the filtered reference frame; and outputting data of the prediction encoded current block and information about the filter.