公开(公告)号：US20250113030A1

公开(公告)日：2025-04-03

申请号：US18979447

申请日：2024-12-12

Applicant: Electronics and Telecommunications Research Institute ,  RESEARCH & BUSINESS FOUNDATION SUNGKYUNKWAN UNIVERSITY

Inventor： Jung Won KANG ,  Ha Hyun LEE ,  Sung Chang LIM ,  Jin Ho LEE ,  Hui Yong KIM ,  Byeung Woo JEON ,  Jee Yoon PARK

IPC: H04N19/12 ,  H04N19/176 ,  H04N19/46 ,  H04N19/61

Abstract: The present specification discloses a method of decoding an image. The method of decoding an image according to the method includes: obtaining transform skip information of a current block from a bitstream; obtaining multiple transform selection information of the current block on the basis of the transform skip information from the bitstream; and performing inverse transform on the current block on the basis of the multiple transform selection information, wherein the multiple transform selection information is used to set each of a horizontal transform type and a vertical transform type.

公开(公告)号：US20250104724A1

公开(公告)日：2025-03-27

申请号：US18886296

申请日：2024-09-16

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

Inventor： Inseon JANG ,  Soo Young PARK ,  Seung Kwon BEACK ,  Jongmo SUNG ,  Woo-taek LIM ,  Byeongho CHO ,  Jung Won KANG ,  Tae Jin LEE ,  Minje KIM ,  Haici YANG

IPC: G10L19/16

Abstract: A method and apparatus for encoding/decoding a neural network-based personalized speech are provided. The method includes outputting a first bit stream in which an input speech signal is encrypted, based on the input speech signal, and outputting a second bit stream in which speaker information of the input speech signal is encrypted, based on the input speech signal.

公开(公告)号：US20250104722A1

公开(公告)日：2025-03-27

申请号：US18886765

申请日：2024-09-16

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

Inventor： Inseon JANG ,  Woo-taek LIM ,  Soo Young PARK ,  Seung Kwon BEACK ,  Jongmo SUNG ,  Byeongho CHO ,  Jung Won KANG ,  Tae Jin LEE ,  Minje KIM ,  Haici YANG

IPC: G10L19/038 ,  G10L21/0208 ,  G10L25/30

Abstract: A method and device for encoding/decoding an audio signal based on dequantization through potential diffusion are provided. The method of decoding an audio signal includes obtaining a discrete latent vector in which a speech signal is quantized and based on the discrete latent vector, outputting a continuous latent vector in which the discrete latent vector is dequantized.

公开(公告)号：US20250095216A1

公开(公告)日：2025-03-20

申请号：US18889565

申请日：2024-09-19

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Soo Woong KIM ,  Gun BANG ,  Ji Hoon DO ,  Seong Jun BAE ,  Jin Ho LEE ,  Ha Hyun LEE ,  Jung Won KANG

IPC: G06T9/00

Abstract: This disclosure provides a method and apparatus for compressing 3-dimensional volume data. The method for encoding a TSDF volume may comprise: lossily encoding magnitude information of a Truncated Signed Distance Field (TSDF) volume based on a hyperprior model; and losslessly encoding sign information of the TSDF volume based on the hyperprior model, wherein the lossy encoding comprises selecting and entropy-encoding some elements from a latent vector for the TSDF volume based on selection information obtained through the hyperprior model.

公开(公告)号：US20250008090A1

公开(公告)日：2025-01-02

申请号：US18828322

申请日：2024-09-09

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

Inventor： 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

IPC: H04N19/105 ,  H04N19/147 ,  H04N19/159 ,  H04N19/176

Abstract: A method and apparatus use a geometric modified image for video encoding/decoding. The encoding method may include: generating a geometric modified reference picture by geometrically modifying a reference picture; generating a prediction block of a current block within an encoding target picture by performing inter prediction by referencing the reference picture or the geometrically modified reference picture; and encoding inter-prediction information of the current block.

公开(公告)号：US20240430404A1

公开(公告)日：2024-12-26

申请号：US18813138

申请日：2024-08-23

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 ,  H04N19/147 ,  H04N19/176 ,  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：US20240388716A1

公开(公告)日：2024-11-21

申请号：US18789109

申请日：2024-07-30

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 ,  H04N19/117 ,  H04N19/124 ,  H04N19/51 ,  H04N19/52 ,  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：US20240373013A1

公开(公告)日：2024-11-07

申请号：US18674647

申请日：2024-05-24

Applicant: Electronics and Telecommunications Research Institute ,  CHIPS&MEDIA, INC

Inventor： Sung Chang LIM ,  Jung Won KANG ,  Ha Hyun LEE ,  Jin Ho LEE ,  Hui Yong KIM ,  Dae Yeon KIM

IPC: H04N19/124 ,  H04N19/159 ,  H04N19/176 ,  H04N19/186

Abstract: Disclosed herein is a method of encoding/decoding an image. The image decoding method includes decoding information on a quantization matrix from a bitstream, acquiring a quantization matrix of a current block based on the information on the quantization matrix, and dequantizing the current block using the quantization matrix of the current block. The acquiring of the quantization matrix of the current block includes deriving a single identifier using at least one of a size of the current block, a prediction mode or a color component, and acquiring the quantization matrix of the current block based on the single identifier.

公开(公告)号：US20240323449A1

公开(公告)日：2024-09-26

申请号：US18675857

申请日：2024-05-28

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE ,  CHIPS&MEDIA, INC ,  INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY ,  INDUSTRY-UNIVERSITY COOPERATION FOUNDATION KOREA AEROSPACE UNIVERSITY

Inventor： Sung Chang LIM ,  Jung Won KANG ,  Ha Hyun LEE ,  Jin Ho LEE ,  Hui Yong KIM ,  Dae Yeon KIM ,  Wook Je JEONG ,  Dong Jin PARK ,  Min Yong JEON ,  Yung Lyul LEE ,  Nam Uk KIM ,  Myung Jun KIM ,  Ji Youn JUNG ,  Jae Gon KIM

IPC: H04N19/82 ,  H04N19/107 ,  H04N19/176

CPC classification number: H04N19/82 ,  H04N19/107 ,  H04N19/176

Abstract: An image decoding is performed by steps including: determining whether or not to perform filtering on a boundary of a current block; determining a filtering strength on the boundary of the current block, and a number of samples used in filtering; and performing filtering on the boundary of the current block on the basis of the filtering strength and the number of samples used in filtering, where the number of samples used in filtering is determined on the basis of a size of the current block.

公开(公告)号：US20240161380A1

公开(公告)日：2024-05-16

申请号：US18503266

申请日：2023-11-07

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Seong Jun BAE ,  Jung Won KANG ,  Soo Woong KIM ,  Ji Hoon DO ,  Gun BANG ,  Jin Ho LEE ,  Ha Hyun LEE

IPC: G06T15/00 ,  G06T9/00

CPC classification number: G06T15/00 ,  G06T9/00

Abstract: A pixel ray crossing-based multi-viewpoint MPI geometry generation method, device, and recording medium of the present disclosure, the method may comprise obtaining a multi-viewpoint image by original cameras which shoot a different viewpoint, obtaining a multi-plane image (MPI) based on the multi-viewpoint image, obtaining, based on the MPI, an atlas image in a 2D form, and obtaining a bitstream by encoding the atlas image.