Samsung Electronics Co., Ltd.

Sungkyunkwan University

Korea Advanced Institute of Science and Technology

Korea University Industrial & Academic Collaboration Foundation

Korea University Industrial Academic Collaboration Foundation

Kwang-pyo Choi

Chan-yul Kim

Young-o Park

Jeong-Hoon Park

Young-hun Joo

Yun-Je Oh

Young-O Park

Il-koo Kim

Jae-hwan Kim

Jong-seok Lee

Sun-young Jeon

Woong-il Choi

Han-Sang Kim

Elena Alshina

Chang-su Kim

Kwan-Woong Song

Yong-Deok Kim

Bong-Soo Jung

Vladyslav Zakharchenko

Hee-chul Yang

Sun-il Lee

Ho-cheon Wey

Kwang-Cheol Choi

Byeung-Woo Jeon

Chang-Sup Shim

Kyung-Ho Chae

Joon-Hyun Lee

Pil-kyu Park

Jae-Kyun Ahn

Jae-Hyun Park

Chang-Hyun Lee

Dae-sung Cho

Alexander Alshin

Min-woo Park

Hyun-jung Kim

Seung-soo Jeong

Dai-woong Choi

Myung-jin Eom

Jeong-seok Choi

In-kwon Choi

Mi-suk Huh

Jung-won Lee

Sung-chan Kim

Myung-ho Kim

Kwang-hyun Won

Min-seok Choi

Chang-hyun Lee

Raj Narayana Gadde

Amith Dsouza

Hee-kwan Lee

Anubhav Singh

Sri Nitchith Akula

Chang-Ick Kim

Won-Jun Kim

Jang-hee Ryu

Seog-chung Seo

Young-jin Kwak

Bong-Gon Kim

Zakharchenko Vladyslav

Ramkumaar Kovil Kanthadai

Chirag Pujara

Denis Gorodetskii

Denis Gorodetskiy

Provided are an inter prediction method and a motion compensation method. The inter prediction method includes: performing inter prediction on a current image by using a long-term reference image stored in a decoded picture buffer; determining residual data and a motion vector of the current image generated via the inter prediction; and determining least significant bit (LSB) information as a long-term reference index indicating the long-term reference image by dividing picture order count (POC) information of the long-term reference image into most significant bit (MSB) information and the LSB information.

Method for inter prediction and device therefor, and method for motion compensation and device therefor

Encoding an image using a non-encoding region of the image, a block-based encoding region of the image, and a pixel-based encoding region of the image.

Encoding method and apparatus using non-encoding region, block-based encoding region, and pixel-based encoding region

Provided are a method and apparatus for encoding or decoding a 360-degree image. An image decoding method and apparatus according to an embodiment include: obtaining image data from a bitstream; decoding a first region of a projection image corresponding to a non-clipping region of a 360-degree image from the image data; obtaining information about a clipping region of the 360-degree image from the bitstream; determining a second region of the projection image, based on the information about the clipping region; and converting the projection image including the first region and the second region into the 360-degree image.

Method and apparatus for encoding or decoding 360 degree image

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

Accordingly embodiments herein disclose a method for producing 360 degree image content on a rectangular projection. The method includes detecting whether at least one discontinuous boundary is present in the 360-degree image content, wherein the at least one discontinuous boundary is detected using the packing of one or more projection segments. Further, the method includes obtaining one or more reconstructed blocks from the 360-degree image content. The reconstructed blocks are generated from the 360 degree image content. Further, the method includes performing one of enabling at least one in-loop filtering function on the one or more reconstructed blocks of the 360 degree image content when the at least one of image content discontinuous boundary is not present and disabling at least one in-loop filtering function on the one or more reconstructed blocks of the 360 degree image content located around the at least one discontinuous boundary.

Method and apparatus for producing 360 degree image content on rectangular projection by selectively applying in-loop filter

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, performed by a terminal, of providing content includes determining whether at least one content is included in preference content, based on information about the at least one content provided to the terminal and preference information of a user of the terminal about content; content, which is not included in the preference content, is present in the at least one content, transmitting, to a server, a request to change the first content to second content included in the preference content based on previously stored information about the preference content; and outputting the second content received from the server, in response to the request.

Method and device for providing content

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

Provided are a method and apparatus for encoding or decoding a 360-degree image. According to an image decoding method and apparatus according to an embodiment, an original 360-degree image is reconstructed by acquiring image data from a bitstream, decoding a projection image of a 360-degree image from the image data, converting the projection image into the 360-degree image, acquiring rotation information of the 360-degree image from the bitstream, and rotating the 360-degree image based on the rotation information.

Method and apparatus for encoding and decoding 360-degree image

Provided is an image processing method including: generating an omnidirectional spherical image; determining information regarding a director's view that indicates some regions of the omnidirectional spherical image; generating a projection image by projecting the omnidirectional spherical image to a development view of a polyhedron; dividing, from the projection image, a director's view projection image corresponding to the director's view, based on the information regarding the director's view; reshaping the director's view projection image into a director's view rectangular image by moving a location of at least one of pixels of the director's view projection image; and generating a bitstream which the director's view rectangular image is encoded into.

Image processing method and apparatus

Provided is an image processing method including: acquiring images captured in at least two directions; generating a projection image by projecting the images onto a polyhedron; moving a location of at least one pixel among pixels in the projection image to reshape the projection image into a rectangular image; and processing the rectangular image.

Method and apparatus for processing image

An image encoding apparatus includes an annexed data obtainer configured to obtain annexed data that is annexed to image data and that is to be transmitted along with the image data; an annexed image data obtainer configured to convert the obtained annexed data and obtain annexed image data having a same format as that of the image data; and an encoder configured to obtain transmission image data based on the annexed image data and the image data and encode the transmission image data according to a first codec.

Image encoding apparatus and image decoding apparatus and method of operating the same

Growing community of inventors

Anyang-si, South Korea

Kwang-pyo Choi