Samsung Electronics Co., Ltd.

Yonsei University

Kyungah Kim

Minsoo Park

Yinji Piao

Kwangpyo Choi

Minwoo Park

Quockhanh Dinh

Chan-yul Kim

Sun-il Lee

Yumi Sohn

Won Woo Ro

Minsik Kim

Pilkyu Park

Tejas Nair

Junghye Min

An image decoding method and apparatus obtain intra prediction feature data of a current block from a bitstream, determine an intra flow indicating a reference pixel of a current pixel in the current block, by applying the intra prediction feature data, neighboring pixels of the current block, and coding context information of the current block to a neural network, obtain a predicted pixel of the current pixel based on the intra flow of the current block, and reconstruct the current block based on the predicted pixel.

Image decoding apparatus and method and image encoding apparatus and method

Provided are an image decoding method and apparatus. The image decoding method includes identifying at least two neighboring sub-blocks that have a same motion vector and are adjacent to each other from among a plurality of neighboring sub-blocks adjacent to a current block, determining a representative motion vector and representative location information corresponding to the at least two neighboring sub-blocks, determining a parameter of a model for determining a motion vector based on the representative motion vector and the representative location information, determining a motion vector of a current sub-block included in the current block, based on location information of the current sub-block and the parameter, and predicting the current block based on the motion vector of the current sub-block wherein the representative motion vector is determined based on the same motion vector, and the representative location information indicates coordinates that are determined based on the at least two neighboring sub-blocks.

Image decoding method and apparatus, and image encoding method and apparatus

A method of decoding an image, including obtaining a motion vector of a current block; obtaining a preliminary prediction block based on a reference block indicated by the motion vector in a reference image; obtaining a final prediction block for the current block by applying, to a neural network, at least one of a picture order count (POC) map including a POC difference between the reference image and a current image including the current block, the preliminary prediction block, and a quantization error map; and reconstructing the current block based on the final prediction block and a residual block obtained from a bitstream, wherein sample values of the quantization error map are calculated based on a quantization parameter for the reference block.

Method and apparatus for image decoding and image encoding using AI prediction block

An entropy decoding method may include obtaining, from a bitstream, information about a slice type, based on an occurrence probability of a symbol, performing arithmetic decoding on a current symbol corresponding to a syntax element, when the information about the slice type indicates an I slice, determining a first scaling factor for updating the occurrence probability of the symbol by using a first function, wherein a value of the first function is determined based on a first threshold value, when the information about the slice type indicates a B or P slice, determining the first scaling factor by using a second function, wherein a value of the second function is determined based on a second threshold value, and by using the first scaling factor, updating the occurrence probability of the symbol.

Entropy encoding and decoding apparatus and method for using the same

An image processing apparatus including a memory storing instructions, and a processor configured to operate based on the instructions to reconstruct a current block from encoded data of the current block, obtain a quantization error map including sample values calculated based on a quantization parameter included in the encoded data, obtain a first modified block by applying the current block and the quantization error map to a neural network, obtain a first differential block between the current block and the first modified block, obtain a second differential block by changing sample values of the first differential block based on a parameter dependent on a feature of the current block, and obtain a second modified block by combining the current block and the second differential block.

Apparatus and method for applying artificial intelligence-based filtering to image

A display apparatus and a controlling method thereof are disclosed. The display apparatus includes: a memory storing one or more instructions; and a processor configured to execute the stored one or more instructions to: obtain encoded data of a first digital image and artificial intelligence (AI) meta-information indicating a specification of a deep neural network (DNN), obtain a second digital image corresponding to the first digital image by decoding the encoded data, obtain a light signal converted from the second digital image according to a previously determined electro-optical transfer function (EOTF), and obtain a display signal by processing the light signal by using an opto-optical transfer function (OOTF) and a high dynamic range (HDR) DNN set according to the AI meta-information.

Image providing apparatus and image providing method thereof, and display apparatus and display method thereof

Provided is an image encoding method including extracting feature points from a picture; generating at least two clusters by performing feature point clustering on the extracted feature points; determining at least two split sections in the picture, the at least two split sections respectively corresponding to the at least two clusters; parallel-encoding the at least two split sections; and generating a bitstream including information about the at least two split sections. A size and a shape of each of the at least two split sections may be individually determined.

Growing community of inventors

Seoul, South Korea

Kyungah Kim