Patents by Inventor Jin-Soo Choi

Jin-Soo Choi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20230297833
    Abstract: Disclosed herein are a method and apparatus for compressing learning parameters for training of a deep-learning model and transmitting the compressed parameters in a distributed processing environment. Multiple electronic devices in the distributed processing system perform training of a neural network. By performing training, parameters are updated. The electronic device may share the updated parameter thereof with additional electronic devices. In order to efficiently share the parameter, the residual of the parameter is provided to the additional electronic devices. When the residual of the parameter is provided, the additional electronic devices update the parameter using the residual of the parameter.
    Type: Application
    Filed: April 24, 2023
    Publication date: September 21, 2023
    Applicant: Electronics and Telecommunications Research Institute
    Inventors: Seung-Hyun CHO, Youn-Hee KIM, Jin-Wuk SEOK, Joo-Young LEE, Woong LIM, Jong-Ho KIM, Dae-Yeol LEE, Se-Yoon JEONG, Hui-Yong KIM, Jin-Soo CHOI, Je-Won KANG
  • Publication number: 20230300362
    Abstract: An image decoding method according to the present invention includes reconstructing a residual block by inverse-quantizing and inverse-transforming an entropy-decoded residual block, generating a prediction block by performing intra prediction on a current block, and reconstructing an picture by adding the reconstructed residual block to the prediction block, wherein generating the prediction block includes generating a final prediction value of a prediction target pixel included in the current block based on a first prediction value of the prediction target pixel and a final correction value calculated by performing an arithmetic right shift on a two's complementary integer representation for an initial correction value of the prediction target pixel by a binary digit of 1. Accordingly, upon image encoding/decoding, computation complexity may be reduced.
    Type: Application
    Filed: May 22, 2023
    Publication date: September 21, 2023
    Inventors: Hui Yong KIM, Jin Ho LEE, Sung Chang LIM, Jin Soo CHOI, Jin Woong KIM
  • Patent number: 11765356
    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.
    Type: Grant
    Filed: May 31, 2022
    Date of Patent: September 19, 2023
    Assignees: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Hui Yong Kim, Sung Chang Lim, Jin Ho Lee, Jin Soo Choi, Jin Woong Kim, Gwang Hoon Park, Kyung Yong Kim
  • Patent number: 11758136
    Abstract: The present invention relates to a method and apparatus for encoding and decoding a video image based on transform. The method for decoding a video includes: determining a transform mode of a current block; inverse-transforming residual data of the current block according to the transform mode of the current block; and rearranging the inverse-transformed residual data of the current block according to the transform mode of the current block, wherein the transform mode includes at least one of SDST (Shuffling Discrete Sine Transform), SDCT (Shuffling Discrete cosine Transform), DST (Discrete Sine Transform) or DCT (Discrete Cosine Transform).
    Type: Grant
    Filed: June 23, 2017
    Date of Patent: September 12, 2023
    Assignees: Electronics and Telecommunications Research Institute, Industry Academy Cooperation Foundation of Sejong University
    Inventors: Sung Chang Lim, Jung Won Kang, Hyun Suk Ko, Jin Ho Lee, Ha Hyun Lee, Dong San Jun, Seung Hyun Cho, Hui Yong Kim, Jin Soo Choi, Yung Lyul Lee, Nam Uk Kim, Jun Woo Choi
  • Patent number: 11758128
    Abstract: The present invention relates to a method and apparatus for video encoding/decoding by using a geometric modified picture. The encoding method according to the present invention includes: generating a geometric modified picture by geometrically modifying a reference picture; and generating a first prediction block of a current block by performing inter prediction referencing the geometric modified picture.
    Type: Grant
    Filed: August 17, 2022
    Date of Patent: September 12, 2023
    Assignees: Electronics and Telecommunications Research Institute, University-Industry Cooperation Group of Kyung Hee University
    Inventors: Jung Won Kang, Hyun Suk Ko, Sung Chang Lim, Jin Ho Lee, Dong San Jun, Hui Yong Kim, Gwang Hoon Park, Jin Soo Choi, Tae Hyun Kim, Dae Young Lee, Young Su Heo
  • Publication number: 20230281960
    Abstract: Disclosed herein is an encoding method. The encoding method includes extracting a feature map from an input image, determining an encoding feature map based on the extracted feature map, generating a converted feature map by performing conversion on the encoding feature map, and performing encoding on the converted feature map.
    Type: Application
    Filed: February 21, 2023
    Publication date: September 7, 2023
    Applicants: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Youn-Hee KIM, Se-Yoon JEONG, Ji-Hoon DO, Joo-Young LEE, Hyoung-Jin KWON, Dong-Hyun KIM, Jong-Ho KIM, Sung-Chang LIM, Woong LIM, Jin-Soo CHOI, Tae-Jin LEE, Hui-Yong KIM, Chang-Kyun CHOI, Jung-Heum KANG, Sung-Ho BAE, Hye-Won JEONG
  • Publication number: 20230276046
    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.
    Type: Application
    Filed: May 4, 2023
    Publication date: August 31, 2023
    Applicant: Electronics and Telecommunications Research Institute
    Inventors: Dong San JUN, Jung Won KANG, Sung Chang LIM, Hyun Suk KO, Jin Ho LEE, Hui Yong KIM, Jin Soo CHOI
  • Publication number: 20230276058
    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.
    Type: Application
    Filed: May 3, 2023
    Publication date: August 31, 2023
    Applicants: Electronics and Telecommunications Research Institute, Kwangwoon University Industry-Academic Collaboration Foundation, University-Industry Cooperation Group of Kyung Hee University
    Inventors: 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
  • Patent number: 11743470
    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.
    Type: Grant
    Filed: October 27, 2021
    Date of Patent: August 29, 2023
    Assignee: Electronics and Telecommunications Research Institute
    Inventors: 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
  • Patent number: 11743486
    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.
    Type: Grant
    Filed: November 12, 2021
    Date of Patent: August 29, 2023
    Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: 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
  • Patent number: 11743473
    Abstract: The present invention relates to a method for encoding/decoding a video. To this end, the method for decoding a video may include: deriving a spatial merge candidate from at least one of spatial candidate blocks of a current block, deriving a temporal merge candidate from a co-located block of the current block, and generating a prediction block of the current block based on at least one of the derived spatial merge candidate and the derived temporal merge candidate, wherein a reference picture for the temporal merge candidate is selected based on a reference picture list of a current picture including the current block and a reference picture list of a co-located picture including the co-located block.
    Type: Grant
    Filed: April 11, 2022
    Date of Patent: August 29, 2023
    Inventors: Dong San Jun, Ha Hyun Lee, Jung Won Kang, Hyun Suk Ko, Sung Chang Lim, Jin Ho Lee, Seung Hyun Cho, Hui Yong Kim, Jin Soo Choi
  • Patent number: 11743491
    Abstract: The image decoding method according to the present invention comprises the steps of: determining the availability of a block adjacent to a current block; configuring a merge candidate list for the current block on the basis of the result of the determined availability; and performing motion compensation for the current block on the basis of the merge candidate list, wherein the step of determining availability comprises the steps of inducing block availability information on the adjacent block and inducing the availability of motion information on the adjacent block, and the step of determining the availability of the adjacent block is such that when there is more than one adjacent block, the availability of adjacent blocks can be determined in accordance with a predetermined order restriction.
    Type: Grant
    Filed: November 5, 2021
    Date of Patent: August 29, 2023
    Assignees: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Hui Yong Kim, Sung Chang Lim, Jin Soo Choi, Jin woong Kim, Gwang Hoon Park, Kyung Yong Kim
  • Publication number: 20230267649
    Abstract: Disclosed is a data transmission system that transmits data by using a relay. The relay selects a transmission terminal from among a plurality of terminals accessing a base station. A base station transmits base station data to the relay during a first time slot, and the transmission terminal transmits terminal data to the relay. The relay transmits terminal data to the base station during a second time slot, and transmits base station data to the transmission terminal.
    Type: Application
    Filed: November 18, 2022
    Publication date: August 24, 2023
    Inventors: Sung Chang LIM, Se Yoon JEONG, Hae Chul CHOI, Jin Soo CHOI, Jin Woo HONG, Yung Lyul LEE, Dae Yeon KIM
  • Patent number: 11736696
    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.
    Type: Grant
    Filed: December 30, 2021
    Date of Patent: August 22, 2023
    Assignee: Electronics and Telecommunications Research Institute
    Inventors: Sung Chang Lim, Hui Yong Kim, Jin Ho Lee, Jin Soo Choi, Jin Woong Kim
  • Patent number: 11729380
    Abstract: An image decoding method, according to the present invention, includes the steps of: deriving an MPM candidate mode from neighboring blocks adjacent to a target block to be decoded; generating an MPM list using the MPM candidate mode derived from the neighboring blocks; and deriving an intra prediction mode for the target block to be decoded using the generated MPM list. According to the present invention, image compression efficiency can be improved.
    Type: Grant
    Filed: January 3, 2022
    Date of Patent: August 15, 2023
    Assignee: Electronics and Telecommunications Research Institute
    Inventors: Jin Ho Lee, Hui Yong Kim, Sung Chang Lim, Jin Soo Choi, Jin Woong Kim
  • Publication number: 20230247194
    Abstract: The present invention relates to an encoding method and decoding method, and a device using the same. The encoding method according to the present invention comprises the steps of: specifying an intra prediction mode for a current block; and scanning a residual signal by intra prediction of the current block, wherein the step of scanning the residual signal can determine a scanning type for a luminance signal and a chroma signal of the current block according to an intra prediction mode for a luminance sample of the current block.
    Type: Application
    Filed: March 28, 2023
    Publication date: August 3, 2023
    Applicants: Electronics and Telecommunications Research Institute, University-Industry Cooperation Group of Kyung Hee University
    Inventors: Hui Yong KIM, Gwang Hoon PARK, Kyung Yong KIM, Sung Chang LIM, Jin Ho LEE, Jin Soo CHOI, Jin Woong KIM
  • Publication number: 20230239466
    Abstract: An image encoding/decoding method and apparatus for predicting a second color component block using a first color component block are provided. An image decoding method of the present invention comprises deriving a prediction parameter using the first color component block, and predicting the second color component block using the derived prediction parameter.
    Type: Application
    Filed: April 4, 2023
    Publication date: July 27, 2023
    Applicant: LX SEMICON CO., LTD
    Inventors: Jin Ho LEE, Hyun Suk KO, Jung Won KANG, Sung Chang LIM, Ha Hyun LEE, Dong San JUN, Seung Hyun CHO, Hui Yong KIM, Jin Soo CHOI
  • Publication number: 20230239467
    Abstract: The present invention relates to an encoding method and decoding method, and a device using the same. The encoding method according to the present invention comprises the steps of: specifying an intra prediction mode for a current block; and scanning a residual signal by intra prediction of the current block, wherein the step of scanning the residual signal can determine a scanning type for a luminance signal and a chroma signal of the current block according to an intra prediction mode for a luminance sample of the current block.
    Type: Application
    Filed: March 28, 2023
    Publication date: July 27, 2023
    Applicants: Electronics and Telecommunications Research Institute, University-Industry Cooperation Group of Kyung Hee University
    Inventors: Hui Yong KIM, Gwang Hoon PARK, Kyung Yong KIM, Sung Chang LIM, Jin Ho LEE, Jin Soo CHOI, Jin Woong KIM
  • Patent number: 11711541
    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.
    Type: Grant
    Filed: March 16, 2021
    Date of Patent: July 25, 2023
    Assignee: Electronics and Telecommunications Research Institute
    Inventors: Jin Ho Lee, Hui Yong Kim, Sung Chang Lim, Jin Soo Choi, Jin Woong Kim
  • Patent number: 11711523
    Abstract: The present invention relates to a method and device for sharing a candidate list. A method of generating a merging candidate list for a predictive block may include: producing, on the basis of a coding block including a predictive block on which a parallel merging process is performed, at least one of a spatial merging candidate and a temporal merging candidate of the predictive block; and generating a single merging candidate list for the coding block on the basis of the produced merging candidate. Thus, it is possible to increase processing speeds for coding and decoding by performing inter-picture prediction in parallel on a plurality of predictive blocks.
    Type: Grant
    Filed: November 15, 2021
    Date of Patent: July 25, 2023
    Assignees: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Hui Yong Kim, Gwang Hoon Park, Kyung Yong Kim, Sang Min Kim, Sung Chang Lim, Jin Ho Lee, Jin Soo Choi, Jin Woong Kim