Samsung Electronics Co., Ltd.

Yonsei University

Sun-young Jeon

Young-o Park

Jeong-Hoon Park

Kwang-pyo Choi

Jae-hwan Kim

Jong-seok Lee

Yun-Je Oh

Min-su Cheon

Young-hun Joo

Yong-hyun Lim

Dosik Hwang

Jinseong Jang

Bong-Gon Kim

Kihun Bang

Hanbyol Jang

Provided is in-loop filtering technology using a trained deep neural network (DNN) filter model. An image decoding method according to an embodiment includes receiving a bitstream of an encoded image, generating reconstructed data by reconstructing the encoded image, obtaining information about a content type of the encoded image from the bitstream, determining a deep neural network (DNN) filter model trained to perform in-loop filtering by using at least one computer, based on the information about the content type, and performing the in-loop filtering by applying the reconstructed data to the determined DNN filter model.

Method and device for encoding or decoding image

Provided is a prediction image generating technology using a deep neural network (DNN). Provided is an image decoding method including: receiving a bitstream of an encoded image; determining at least one block split from the encoded image; determining neighboring blocks for predicting a current block among the at least one block; generating prediction data of the current block by applying the neighboring blocks to a DNN learning model configured to predict a block of an image by using at least one computer; extracting residual data of the current block from the bitstream; and reconstructing the current block by using the prediction data and the residual data.

Provided are an image compressing method including determining a compressed image by performing downsampling using a deep neural network (DNN) on an image; determining a prediction signal by performing prediction based on the compressed image; determining a residual signal based on the compressed image and the prediction signal; and generating a bitstream comprising information about the residual signal, wherein the DNN has a network structure that is predetermined according to training of a downsampling process using information generated in an upsampling process, and an image compressing device for performing the image compressing method. Also, provided are an image reconstructing method of reconstructing a compressed image by using a DNN for upsampling, the compressed image having been compressed by the image compressing method, and an image reconstructing device for performing the image reconstructing method.

Method for encoding/decoding image and device therefor

Provided is a method of encoding an image, the method including: determining a subjective quality of the image when the image is compressed; determining at least one degree of compression that changes the subjective quality and is from among degrees of compression indicating how much the image is compressed; and encoding the image by compressing a residual signal of the image, based on compression information according to the determined degree of compression, wherein the subjective quality is determined for each frame by using a Deep Neural Network (DNN). Provided are an image decoding method and an image decoding apparatus for performing the image decoding method for decoding an image by using information encoded according to an image encoding method.

Method for encoding/decoding image, and device therefor

An electronic apparatus includes a memory configured to store a predetermined conversion relation, and a processor configured to obtain first luminance information indicating luminance values of respective pixels included in a first image, and obtain first color information indicating color values of the respective pixels, obtain a first cumulative distribution function indicating a relation between a cumulative pixel count and each luminance level based on the first luminance information, obtain a second cumulative distribution function by applying the predetermined conversion relation to the first cumulative distribution function, calculate second luminance information indicating converted luminance values of the respective pixels by using the first cumulative distribution function and the second cumulative distribution function, and generate a second image based on the first color information and the second luminance information.

Electronic apparatus and controlling method of thereof

A Frame Rate Conversion (FRC) method using motion interpolation is disclosed. The FRC method includes checking the position of a motion vector intersecting an interpolated frame for each block of the interpolated frame, performing motion interpolation by acquiring a motion vector of each vertex of each block using motion vectors adjacent to each vertex, and performing motion interpolation on pixels of each block using the motion vector of each vertex.

Growing community of inventors

Anyang-si, South Korea

Sun-young Jeon