-
公开(公告)号：US12277073B2
公开(公告)日：2025-04-15
申请号：US18472137
申请日：2023-09-21
Inventor： Young Ho Gong , Woo Hyuck Park , Ye Bin Kwon , Donggyu Sim
Abstract: According to a quantization interconnect apparatus and an operating method thereof according to the exemplary embodiment of the present disclosure, in a quantization artificial neural network accelerator system, the quantization is performed in the interconnect bus according to a precision without separate processing of the CPU/GPU so that as compared with the quantization by a host processor and an accelerator according to a quantization method of the related art, a number of instructions is reduced to improve the performance/memory efficiency. Further, a computational burden of the host process is reduced to reduce the power and improve the performance.
-
公开(公告)号：US20250118310A1
公开(公告)日：2025-04-10
申请号：US18982631
申请日：2024-12-16
Applicant: Electronics and Telecommunications Research Institute , KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
Inventor： Tae Jin LEE , Seung-Kwon BAEK , Min Je KIM , Dae Young JANG , Jeongil SEO , Kyeongok KANG , Jin-Woo HONG , Hochong PARK , Young-Cheol PARK
Abstract: Provided is an encoding apparatus for integrally encoding and decoding a speech signal and a audio signal, and may include: an input signal analyzer to analyze a characteristic of an input signal; a stereo encoder to down mix the input signal to a mono signal when the input signal is a stereo signal, and to extract stereo sound image information; a frequency band expander to expand a frequency band of the input signal; a sampling rate converter to convert a sampling rate; a speech signal encoder to encode the input signal using a speech encoding module when the input signal is a speech characteristics signal; a audio signal encoder to encode the input signal using a audio encoding module when the input signal is a audio characteristic signal; and a bitstream generator to generate a bitstream.
-
公开(公告)号：US20250071294A1
公开(公告)日：2025-02-27
申请号：US18947251
申请日：2024-11-14
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 , H04N19/105 , H04N19/11 , H04N19/117 , H04N19/124 , H04N19/132 , H04N19/147 , H04N19/172 , H04N19/176 , H04N19/182 , H04N19/43 , H04N19/44 , H04N19/50 , H04N19/51 , H04N19/587 , H04N19/593 , H04N19/61 , H04N19/615 , H04N19/625 , H04N19/70 , H04N19/91
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：US20250016364A1
公开(公告)日：2025-01-09
申请号：US18891717
申请日：2024-09-20
Applicant: HYUNDAI MOTOR COMPANY , KIA CORPORATION , KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
Inventor： Dong Gyu Sim , Jong Seok Lee , Seung Wook Park , Wha Pyeong Lim
IPC: H04N19/53 , H04N19/117 , H04N19/139 , H04N19/176 , H04N19/196 , H04N19/70
Abstract: Methods encode or decode a picture sequence, some having different resolutions, and store a bitstream of encoded video data. A decoding method includes decoding a first syntax for specifying a reference size of pictures referring to a high-level syntax structure and decoding a second syntax element for specifying a picture size scaled from the reference size of the pictures referring to the high-level syntax structure. The method includes deriving at least one offset factor and at least one scale factor representing a scale difference between a current picture including a current block to be decoded and a reference picture referred to by the current block. The method includes generating a prediction block of the current block from the reference picture by using the motion vector of the current block, the at least one scale factor, and the at least one offset factor, reconstructing a residual block from the bitstream, and reconstructing the current block based on adding the prediction block and the residual block.
-
公开(公告)号：US12192452B2
公开(公告)日：2025-01-07
申请号：US18355415
申请日：2023-07-20
Inventor： Dong Gyu Sim , Sea Nae Park
IPC: H04N19/176 , H04N19/115 , H04N19/186 , H04N19/44
Abstract: A method and apparatus for processing a video signal according to the present invention derives a first prediction value of a chrominance block using a sample of a luminance block, calculates a compensation parameter based on a predetermined reference area, derives a second prediction value of a chrominance block, and reconstructs a chrominance block based on a second prediction value of a chrominance block.
-
Patent Agency Ranking
公开(公告)号：US20240430468A1
公开(公告)日：2024-12-26
申请号：US18829712
申请日：2024-09-10
Applicant: Hyundai Motor Company , Kia Corporation , Kwangwoon University Industry-Academic Collaboration Foundation
Inventor： Dong Gyu Sim , Sea Nae Park , Han Sol Choi , Seung Wook Park , Wha Pyeong Lim
IPC: H04N19/44 , H04N19/105 , H04N19/117 , H04N19/119 , H04N19/176 , H04N19/82 , H04N19/96
Abstract: For encoding and decoding images, an image encoding device divides each picture into sub-pictures that can be independently displayed, and signals layout information about the sub-pictures, and an image decoding device identifies each sub-block through the layout information and decodes the sub-pictures. A video decoding apparatus and method are configured to decode a bitstream containing an encoded sequence of pictures which are partitioned into a plurality of subpictures including a plurality of coding tree blocks.
-
公开(公告)号：US20240388702A1
公开(公告)日：2024-11-21
申请号：US18789079
申请日：2024-07-30
Applicant: HYUNDAI MOTOR COMPANY , KIA CORPORATION , KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
Inventor： Jin Heo , Seung Wook Park , Min Hun Lee , Dong Gyu Sim , Joo Hyung Byeon
IPC: H04N19/11 , H04N19/159 , H04N19/176 , H04N19/196
Abstract: A method is disclosed for composing a MPM list in intra prediction. A video coding method and an apparatus derive intra-prediction modes for neighboring blocks that are non-usable for composing a Most Probable Mode list (MPM list) to organize the derived intra-prediction modes into an MPM list. The video coding method and the apparatus organize, based on history-based MPM list composition, the intra-prediction modes of non-adjacent blocks into a MPM list.
-
公开(公告)号：US12148438B2
公开(公告)日：2024-11-19
申请号：US17373243
申请日：2021-07-12
Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE , KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
Inventor： Seung Kwon Beack , Tae Jin Lee , Min Je Kim , Dae Young Jang , Kyeongok Kang , Jin Woo Hong , Ho Chong Park , Young-cheol Park
IPC: G10L19/022 , G10L19/02 , G10L19/18
Abstract: An encoding apparatus and a decoding apparatus in a transform between a Modified Discrete Cosine Transform (MDCT)-based coder and a different coder are provided. The encoding apparatus may encode additional information to restore an input signal encoded according to the MDCT-based coding scheme, when switching occurs between the MDCT-based coder and the different coder. Accordingly, an unnecessary bitstream may be prevented from being generated, and minimum additional information may be encoded.
-
公开(公告)号：US12114008B2
公开(公告)日：2024-10-08
申请号：US17765391
申请日：2020-09-29
Applicant: HYUNDAI MOTOR COMPANY , KIA CORPORATION , KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
Inventor： Dong Gyu Sim , Jong Seok Lee , Seung Wook Park , Wha Pyeong Lim
IPC: H04N7/12 , H04N19/117 , H04N19/139 , H04N19/176 , H04N19/196 , H04N19/53 , H04N19/70
CPC classification number: H04N19/53 , H04N19/117 , H04N19/139 , H04N19/176 , H04N19/196 , H04N19/70
Abstract: A video decoding apparatus is provided for decoding a sequence of pictures, some of which have different resolutions. The apparatus decodes, from a high-level syntax structure of the sequence, a first syntax element for specifying a reference size of pictures referring to the high-level syntax structure and a second syntax element for specifying a picture size scaled from the reference size of the picture referring to the high-level syntax structure. The apparatus predicts a current block, by modifying a sample position in a reference picture indicated by a motion vector of the current block based on the first and second syntax elements.
-
公开(公告)号：US20240333979A1
公开(公告)日：2024-10-03
申请号：US18737419
申请日：2024-06-07
Applicant: HYUNDAI MOTOR COMPANY , KIA CORPORATION , KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
Inventor： Sea Nae Park , Joo Hyung Byeon , Dong Gyu Sim , Jin Heo , Seung Wook Park
IPC: H04N19/82 , H04N19/117 , H04N19/124 , H04N19/167 , H04N19/176 , H04N19/86
CPC classification number: H04N19/82 , H04N19/117 , H04N19/124 , H04N19/167 , H04N19/176 , H04N19/86
Abstract: A method and an apparatus are disclosed for in-loop filtering in mapping-based video coding. A video coding method and an apparatus compensate for variations in signal characteristics between blocks or within a block by using in-loop filtering when original signals or residual signals are mapped in a particular way and then video encoding or video decoding is performed.
-
-
-
-
-
-
-
-
-
Search Results
334
records
(took 0.027 seconds)
