公开(公告)号：US20210266528A1

公开(公告)日：2021-08-26

申请号：US17315637

申请日：2021-05-10

Applicant: Electronics and Telecommunications Research Institute

Inventor： Dong San JUN ,  Jung Won KANG ,  Sung Chang LIM ,  Hyun Suk KO ,  Jin Ho LEE ,  Hui Yong KIM ,  Jin Soo CHOI

IPC: H04N19/105 ,  H04N19/119 ,  H04N19/176 ,  H04N19/147 ,  H04N19/573

Abstract: The present invention provides a method and apparatus for encoding/decoding an image to enhance inter prediction. According to the present invention, the method includes: determining a first reference picture and a second reference picture of a current block; determining both a first reference block in the first reference picture and a second reference block in the second reference picture; partitioning the current block into a plurality of sub blocks; and obtaining a prediction block of each of the sub blocks on the basis of reference candidate block index information of each of the sub blocks.

公开(公告)号：US20210233547A1

公开(公告)日：2021-07-29

申请号：US17156006

申请日：2021-01-22

Applicant: Electronics and Telecommunications Research Institute ,  The Trustees of Indiana University

Inventor： Mi Suk LEE ,  Seung Kwon BEACK ,  Jongmo SUNG ,  Tae Jin LEE ,  Jin Soo CHOI ,  Minje KIM ,  Kai ZHEN

IPC: G10L19/038 ,  G10L25/18 ,  G10L25/30 ,  G10L25/21 ,  G10L19/028 ,  G06N3/08

Abstract: A method and apparatus for processing an audio signal are disclosed. According to an example embodiment, a method of processing an audio signal may include acquiring a final audio signal for an initial audio signal using a plurality of neural network models generating output audio signals by encoding and decoding input audio signals, calculating a difference between the initial audio signal and the final audio signal in a time domain, converting the initial audio signal and the final audio signal into Mel-spectra, calculating a difference between the Mel-spectra of the initial audio signal and the final audio signal in a frequency domain, training the plurality of neural network models based on results calculated in the time domain and the frequency domain, and generating a new final audio signal distinguished from the final audio signal from the initial audio signal using the trained neural network models.

公开(公告)号：US20210203986A1

公开(公告)日：2021-07-01

申请号：US17202935

申请日：2021-03-16

Applicant: Electronics and Telecommunications Research Institute

Inventor： Jin Ho LEE ,  Hui Yong KIM ,  Sung Chang LIM ,  Jin Soo CHOI ,  Jin Woong KIM

IPC: H04N19/593 ,  H04N19/117 ,  H04N19/157 ,  H04N19/182 ,  H04N19/105 ,  H04N19/159 ,  H04N19/11 ,  H04N19/122 ,  H04N19/137 ,  H04N19/82 ,  H04N19/44 ,  H04N19/136 ,  H04N19/80

Abstract: According to the present invention, an image encoding/decoding method comprises the steps of: performing an intra prediction on a current block so as to generate a prediction block; performing filtering on a filtering target pixel in the prediction block on the basis of the intra prediction mode of the current block so as to generate a final prediction block; and generating a reconstructed block on the basis of a reconstructed differential block corresponding to the current block and on the final prediction block. According to the present invention, image encoding/decoding efficiency can be improved.

公开(公告)号：US20210142812A1

公开(公告)日：2021-05-13

申请号：US17098090

申请日：2020-11-13

Applicant: Electronics and Telecommunications Research Institute ,  The Trustees of Indiana University

Inventor： Minje KIM ,  Kai ZHEN ,  Mi Suk LEE ,  Seung Kwon BEACK ,  Jongmo SUNG ,  Tae Jin LEE ,  Jin Soo CHOI

IPC: G10L19/08 ,  G10L19/032 ,  G10L19/26 ,  G10L21/0208 ,  G10L25/30 ,  G10L13/02 ,  G06N3/08

Abstract: Disclosed are a method for coding a residual signal of LPC coefficients based on collaborative quantization and a computing device for performing the method. The residual signal coding method includes: generating encoded LPC coefficients and LPC residual signals by performing LPC analysis and quantization on an input speech; Determining a predicted LPC residual signal by applying the LPC residual signal to cross module residual learning; Performing LPC synthesis using the coded LPC coefficients and the predicted LPC residual signal; It may include the step of determining an output speech that is a synthesized output according to a result of performing the LPC synthesis.

公开(公告)号：US20210127121A1

公开(公告)日：2021-04-29

申请号：US17141509

申请日：2021-01-05

Applicant: Electronics and Telecommunications Research Institute ,  Kwangwoon University Industry-Academic Collaboration Foundation ,  University-Industry Cooperation Group of Kyung Hee University

Inventor： Hae Chul CHOI ,  Se Yoon JEONG ,  Sung-Chang LIM ,  Jin Soo CHOI ,  Jin Woo HONG ,  Dong Gyu SIM ,  Seoung-Jun OH ,  Chang-Beom AHN ,  Gwang Hoon PARK ,  Seung Ryong KOOK ,  Sea-Nae PARK ,  Kwang-Su JEONG

IPC: H04N19/159 ,  H04N19/132 ,  H04N19/587 ,  H04N19/593 ,  H04N19/61 ,  H04N19/70 ,  H04N19/11 ,  H04N19/124 ,  H04N19/44 ,  H04N19/50 ,  H04N19/625 ,  H04N19/91 ,  H04N19/147 ,  H04N19/176 ,  H04N19/182 ,  H04N19/51 ,  H04N19/615 ,  H04N19/105 ,  H04N19/117 ,  H04N19/43

Abstract: The present invention relates to an image encoding and decoding technique, and more particularly, to an image encoder and decoder using unidirectional prediction. The image encoder includes a dividing unit to divide a macro block into a plurality of sub-blocks, a unidirectional application determining unit to determine whether an identical prediction mode is applied to each of the plurality of sub-blocks, and a prediction mode determining unit to determine a prediction mode with respect to each of the plurality of sub-blocks based on a determined result of the unidirectional application determining unit.

公开(公告)号：US20210112249A1

公开(公告)日：2021-04-15

申请号：US17130042

申请日：2020-12-22

Applicant: Electronics and Telecommunications Research Institute ,  UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY

Inventor： Hui Yong KIM ,  Sung Chang LIM ,  Jin Ho LEE ,  Jin Soo CHOI ,  Jin Woong KIM ,  Gwang Hoon PARK ,  Kyung Yong KIM

IPC: H04N19/129 ,  H04N19/176 ,  H04N19/70 ,  H04N19/122 ,  H04N19/159 ,  H04N19/119 ,  H04N19/136 ,  H04N19/61 ,  H04N19/593 ,  H04N19/625 ,  H04N19/124 ,  H04N19/157 ,  H04N19/44

Abstract: A method and a device for encoding/decoding images are disclosed. The method for encoding images comprises the steps of: deriving a scan type of a residual signal for a current block according to whether or not the current block is a transform skip block; and applying the scan type to the residual signal for the current block, wherein the transform skip block is a block to which transform for the current block is not applied and is specified on the basis of information indicating whether or not transform for the current block is to be applied.

公开(公告)号：US20210051330A1

公开(公告)日：2021-02-18

申请号：US17038332

申请日：2020-09-30

Applicant: Electronics and Telecommunications Research Institute

Inventor： Sung Chang LIM ,  Jung Won KANG ,  Ha Hyun LEE ,  Dong San JUN ,  Hyun Suk KO ,  Jin Ho LEE ,  Seung Hyun CHO ,  Hui Yong KIM ,  Jin Soo CHOI

IPC: H04N19/139 ,  H04N19/52 ,  H04N19/51 ,  H04N19/117 ,  H04N19/124 ,  H04N19/91

Abstract: The present invention relates to a method of performing motion compensation by using motion vector prediction. To this end, a method of decoding an image may include: generating multiple motion vector candidate lists according to an inter-prediction direction of a current block; deriving multiple motion vectors for the current block by using the multiple motion vector candidate lists; determining multiple prediction blocks for the current block by using the multiple motion vectors; and obtaining a final prediction block for the current block based on the multiple prediction blocks.

公开(公告)号：US20200382785A1

公开(公告)日：2020-12-03

申请号：US16998519

申请日：2020-08-20

Applicant: ELectronics and Telecommunications Research Institute ,  UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY

Inventor： Hui Yong KIM ,  Sung Chang LIM ,  Jin Ho LEE ,  Jin Soo CHOI ,  Jin Woong KIM ,  Gwang Hoon PARK ,  Kyung Yong KIM

IPC: H04N19/129 ,  H04N19/176 ,  H04N19/70 ,  H04N19/122 ,  H04N19/159 ,  H04N19/119 ,  H04N19/136 ,  H04N19/61 ,  H04N19/593 ,  H04N19/625 ,  H04N19/124 ,  H04N19/157 ,  H04N19/44

Abstract: A method and a device for encoding/decoding images are disclosed. The method for encoding images comprises the steps of: deriving a scan type of a residual signal for a current block according to whether or not the current block is a transform skip block; and applying the scan type to the residual signal for the current block, wherein the transform skip block is a block to which transform for the current block is not applied and is specified on the basis of information indicating whether or not transform for the current block is to be applied.

公开(公告)号：US20200296412A1

公开(公告)日：2020-09-17

申请号：US16887370

申请日：2020-05-29

Applicant: Electronics and Telecommunications Research Institute

Inventor： Sung Chang LIM ,  Hui Yong KIM ,  Se Yoon JEONG ,  Suk Hee CHO ,  Jong Ho KIM ,  Ha Hyun LEE ,  Jin Ho LEE ,  Jin Soo CHOI ,  Jin Woong KIM ,  Chie Teuk AHN

IPC: H04N19/52

Abstract: An inter prediction method according to the present invention comprises: a step for deriving reference motion information related to a unit to be decoded in a current picture; and a step for performing motion compensation for the unit to be decoded, using the reference motion information that has been derived. According to the present invention, image encoding/decoding efficiency can be enhanced.

公开(公告)号：US20200296376A1

公开(公告)日：2020-09-17

申请号：US16885955

申请日：2020-05-28

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Sung Chang LIM ,  Hui Yong KIM ,  Jin Ho LEE ,  Jin Soo CHOI ,  Jin Woong KIM

IPC: H04N19/126 ,  H04N19/159 ,  H04N19/61 ,  H04N19/196 ,  H04N19/70 ,  H04N19/50 ,  H04N19/463

Abstract: The present invention relates to a method for encoding and decoding a quantized matrix and an apparatus using same, the method for encoding a quantized matrix according to the present invention comprising the steps of: determining a quantization matrix to be used for quantization and quantizing; determining the prediction method used for the quantization of the quantization matrix; and encoding quantization matrix information on the basis of the determined prediction method, wherein the prediction method can be either a prediction method between coefficients in the quantization matrix or a duplicate of the quantization matrix.